# Dedicated deployments — deployable models Open-weight models sference can deploy on GPU capacity reserved for you, behind a private OpenAI-compatible endpoint on European GPUs. Billed per GPU-hour on monthly commitments. Request a deployment for any model at https://sference.com/dedicated (or a model not listed: hello@sference.com). Facts from Hugging Face, synced 2026-10-27. Serverless per-token models: https://sference.com/models.md ## By maker - [Qwen](https://sference.com/models/Qwen.md): 56 models - [Google](https://sference.com/models/google.md): 19 models - [NVIDIA](https://sference.com/models/nvidia.md): 17 models - [DeepSeek](https://sference.com/models/deepseek-ai.md): 16 models - [Z.ai](https://sference.com/models/zai-org.md): 16 models - [Mistral AI](https://sference.com/models/mistralai.md): 12 models - [Moonshot AI](https://sference.com/models/moonshotai.md): 10 models - [Tencent](https://sference.com/models/tencent.md): 8 models - [MiniMax](https://sference.com/models/MiniMaxAI.md): 7 models - [Microsoft](https://sference.com/models/microsoft.md): 7 models - [OpenBMB](https://sference.com/models/openbmb.md): 6 models - [IBM](https://sference.com/models/ibm-granite.md): 6 models - [OpenAI](https://sference.com/models/openai.md): 5 models - [Xiaomi MiMo](https://sference.com/models/XiaomiMiMo.md): 5 models - [Meta Llama](https://sference.com/models/meta-llama.md): 5 models - [Liquid AI](https://sference.com/models/LiquidAI.md): 5 models - [Jina AI](https://sference.com/models/jinaai.md): 5 models - [inclusionAI](https://sference.com/models/inclusionAI.md): 5 models - [Baidu](https://sference.com/models/baidu.md): 4 models - [Cohere](https://sference.com/models/CohereLabs.md): 4 models - [StepFun](https://sference.com/models/stepfun-ai.md): 4 models - [Alibaba NLP](https://sference.com/models/Alibaba-NLP.md): 4 models - [BAAI](https://sference.com/models/BAAI.md): 3 models - [ByteDance Seed](https://sference.com/models/ByteDance-Seed.md): 3 models - [Meta Muse](https://sference.com/models/meta-models.md): 2 models - [Resemble AI](https://sference.com/models/ResembleAI.md): 2 models - [Thinking Machines](https://sference.com/models/thinkingmachines.md): 2 models - [poolside](https://sference.com/models/poolside.md): 2 models - [Hugging Face](https://sference.com/models/HuggingFaceTB.md): 2 models - [PaddlePaddle](https://sference.com/models/PaddlePaddle.md): 2 models - [Nomic](https://sference.com/models/nomic-ai.md): 2 models - [Upstage](https://sference.com/models/upstage.md): 2 models - [Moondream](https://sference.com/models/moondream.md): 2 models - [Swiss AI Initiative](https://sference.com/models/swiss-ai.md): 2 models - [Meituan LongCat](https://sference.com/models/meituan-longcat.md): 2 models - [hexgrad](https://sference.com/models/hexgrad.md): 1 model - [pyannote](https://sference.com/models/pyannote.md): 1 model - [Fish Audio](https://sference.com/models/fishaudio.md): 1 model - [Datalab](https://sference.com/models/datalab-to.md): 1 model - [Aleph Alpha](https://sference.com/models/Aleph-Alpha.md): 1 model - [XingChen AGI](https://sference.com/models/XingChen-AGI.md): 1 model - [LightOn](https://sference.com/models/lightonai.md): 1 model - [Sesame](https://sference.com/models/sesame.md): 1 model - [FunAudioLLM](https://sference.com/models/FunAudioLLM.md): 1 model - [dots.ocr](https://sference.com/models/dots-studio.md): 1 model - [Nari Labs](https://sference.com/models/nari-labs.md): 1 model - [intfloat](https://sference.com/models/intfloat.md): 1 model - [Reflection AI](https://sference.com/models/reflection.md): 1 model - [Kwaipilot](https://sference.com/models/Kwaipilot.md): 1 model - [Snowflake](https://sference.com/models/Snowflake.md): 1 model - [Canopy Labs](https://sference.com/models/canopylabs.md): 1 model - [IndexTeam](https://sference.com/models/IndexTeam.md): 1 model - [Perplexity](https://sference.com/models/perplexity-ai.md): 1 model - [Nanonets](https://sference.com/models/nanonets.md): 1 model - [LG AI Research](https://sference.com/models/LGAI-EXAONE.md): 1 model - [Reducto](https://sference.com/models/reducto.md): 1 model - [Kyutai](https://sference.com/models/kyutai.md): 1 model - [ServiceNow](https://sference.com/models/ServiceNow-AI.md): 1 model - [ZeroEntropy](https://sference.com/models/zeroentropy.md): 1 model - [OpenDataLab](https://sference.com/models/opendatalab.md): 1 model - [Ai2](https://sference.com/models/allenai.md): 1 model - [Mixedbread](https://sference.com/models/mixedbread-ai.md): 1 model - [InternLM](https://sference.com/models/internlm.md): 1 model - [EuroLLM](https://sference.com/models/utter-project.md): 1 model ## Chat & reasoning | Model | Maker | Params | Context | License | Page | | --- | --- | --- | --- | --- | --- | | DeepSeek-V4.1-Flash | DeepSeek | 763B | 1M | MIT | https://sference.com/models/deepseek-ai/DeepSeek-V4.1-Flash.md | | GLM-5.3-Flash | Z.ai | 321B | 1M | MIT | https://sference.com/models/zai-org/GLM-5.3-Flash.md | | GLM-5.3 | Z.ai | 753B | 1M | Custom license | https://sference.com/models/zai-org/GLM-5.3.md | | DeepSeek-V4-Flash-0731 | DeepSeek | 304B | 1M | MIT | https://sference.com/models/deepseek-ai/DeepSeek-V4-Flash-0731.md | | MiniMax-M3.1-Flash | MiniMax | 220B | 1M | Custom license | https://sference.com/models/MiniMaxAI/MiniMax-M3.1-Flash.md | | Qwen3.8-27B | Qwen | 28B | 1M | Apache 2.0 | https://sference.com/models/Qwen/Qwen3.8-27B.md | | Kimi-K3 | Moonshot AI | 2.78T | 1M | Custom license | https://sference.com/models/moonshotai/Kimi-K3.md | | Qwen3.8-Flash-Next | Qwen | 180B | 1M | Custom license | https://sference.com/models/Qwen/Qwen3.8-Flash-Next.md | | DeepSeek-V4-Flash | DeepSeek | 291B | 1M | MIT | https://sference.com/models/deepseek-ai/DeepSeek-V4-Flash.md | | gemma-4-31B-it | Google | 31B | 256K | Apache 2.0 | https://sference.com/models/google/gemma-4-31B-it.md | | MiMo-V2.6-Flash-RL | Xiaomi MiMo | 311B | 1M | MIT | https://sference.com/models/XiaomiMiMo/MiMo-V2.6-Flash-RL.md | | Qwen3.6-35B-A3B | Qwen | 36B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3.6-35B-A3B.md | | gpt-oss-120b | OpenAI | 117B | 128K | Apache 2.0 | https://sference.com/models/openai/gpt-oss-120b.md | | gpt-oss-20b | OpenAI | 21B | 128K | Apache 2.0 | https://sference.com/models/openai/gpt-oss-20b.md | | Qwen3.5-9B | Qwen | 9.7B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3.5-9B.md | | Hy4-preview | Tencent | 780B | 1M | Apache 2.0 | https://sference.com/models/tencent/Hy4-preview.md | | DeepSeek-R1 | DeepSeek | 684B | 160K | MIT | https://sference.com/models/deepseek-ai/DeepSeek-R1.md | | Qwen3-8B | Qwen | 8.2B | 40K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-8B.md | | gemma-4-E4B-it | Google | 8.0B | 128K | Apache 2.0 | https://sference.com/models/google/gemma-4-E4B-it.md | | gemma-4-26B-A4B-it | Google | 26B | 256K | Apache 2.0 | https://sference.com/models/google/gemma-4-26B-A4B-it.md | | NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | NVIDIA | 561B | 1M | OpenMDW 1.1 | https://sference.com/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16.md | | Qwen3-0.6B | Qwen | 752M | 40K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-0.6B.md | | MiniCPM5-2B | OpenBMB | 2.5B | 128K | Apache 2.0 | https://sference.com/models/openbmb/MiniCPM5-2B.md | | DeepSeek-V4-Pro | DeepSeek | 1.6T | 1M | MIT | https://sference.com/models/deepseek-ai/DeepSeek-V4-Pro.md | | Muse-Glimmer-30B | Meta Muse | 30B | 128K | Apache 2.0 | https://sference.com/models/meta-models/Muse-Glimmer-30B.md | | Qwen3.5-4B | Qwen | 4.7B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3.5-4B.md | | gemma-4-12B-it | Google | 12B | 256K | Apache 2.0 | https://sference.com/models/google/gemma-4-12B-it.md | | Qwen3.6-27B | Qwen | 28B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3.6-27B.md | | Inkling | Thinking Machines | 952B | 1M | Apache 2.0 | https://sference.com/models/thinkingmachines/Inkling.md | | gemma-3-1b-it | Google | 1000M | — | Gemma Terms of Use | https://sference.com/models/google/gemma-3-1b-it.md | | GLM-5.2 | Z.ai | 753B | 1M | MIT | https://sference.com/models/zai-org/GLM-5.2.md | | GLM-4.7-Flash | Z.ai | 31B | 195K | MIT | https://sference.com/models/zai-org/GLM-4.7-Flash.md | | Llama-3.3-70B-Instruct | Meta Llama | 71B | 128K | Llama 3.3 Community License | https://sference.com/models/meta-llama/Llama-3.3-70B-Instruct.md | | Qwen3.5-35B-A3B | Qwen | 36B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3.5-35B-A3B.md | | MiniMax-M3 | MiniMax | 427B | 1M | Custom license | https://sference.com/models/MiniMaxAI/MiniMax-M3.md | | Qwen3-4B-Instruct-2507 | Qwen | 4.0B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-4B-Instruct-2507.md | | gemma-4-E2B-it | Google | 5.1B | 128K | Apache 2.0 | https://sference.com/models/google/gemma-4-E2B-it.md | | GLM-5.1 | Z.ai | 754B | 200K | MIT | https://sference.com/models/zai-org/GLM-5.1.md | | Hy3 | Tencent | 299B | 256K | Apache 2.0 | https://sference.com/models/tencent/Hy3.md | | gemma-3-4b-it | Google | 4.3B | 128K | Gemma Terms of Use | https://sference.com/models/google/gemma-3-4b-it.md | | Qwen3.5-27B | Qwen | 28B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3.5-27B.md | | Qwen3.8-2.4T-A95B | Qwen | 2.45T | 1M | Custom license | https://sference.com/models/Qwen/Qwen3.8-2.4T-A95B.md | | MiniMax-M2.5 | MiniMax | 229B | 200K | Modified MIT | https://sference.com/models/MiniMaxAI/MiniMax-M2.5.md | | Kolibri-1 | Aleph Alpha | 78B | 256K | Apache 2.0 | https://sference.com/models/Aleph-Alpha/Kolibri-1.md | | Kimi-K2.5 | Moonshot AI | 1.03T | 256K | Modified MIT | https://sference.com/models/moonshotai/Kimi-K2.5.md | | LFM2.5-2.6B | Liquid AI | 2.7B | 125K | Custom license | https://sference.com/models/LiquidAI/LFM2.5-2.6B.md | | Xing4.0-29B-A4B | XingChen AGI | 31B | 256K | Apache 2.0 | https://sference.com/models/XingChen-AGI/Xing4.0-29B-A4B.md | | medgemma-4b-it | Google | 4.3B | — | Custom license | https://sference.com/models/google/medgemma-4b-it.md | | MiMo-V2.6-Pro-RL | Xiaomi MiMo | 1.02T | 1M | MIT | https://sference.com/models/XiaomiMiMo/MiMo-V2.6-Pro-RL.md | | Qwen3-14B | Qwen | 15B | 40K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-14B.md | | GLM-4.7 | Z.ai | 358B | 200K | MIT | https://sference.com/models/zai-org/GLM-4.7.md | | gemma-3-27b-it | Google | 27B | 128K | Gemma Terms of Use | https://sference.com/models/google/gemma-3-27b-it.md | | GLM-5 | Z.ai | 754B | 200K | MIT | https://sference.com/models/zai-org/GLM-5.md | | Qwen3.5-0.8B | Qwen | 873M | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3.5-0.8B.md | | Step-5-Preview | StepFun | 604B | 1M | Custom license | https://sference.com/models/stepfun-ai/Step-5-Preview.md | | Phi-4-mini-instruct | Microsoft | 3.8B | 128K | MIT | https://sference.com/models/microsoft/Phi-4-mini-instruct.md | | Muse-Spark-Open-816B-A42B | Meta Muse | 822B | 1M | Custom license | https://sference.com/models/meta-models/Muse-Spark-Open-816B-A42B.md | | Kimi-K2.6 | Moonshot AI | 1.03T | 256K | Modified MIT | https://sference.com/models/moonshotai/Kimi-K2.6.md | | Qwen3-1.7B | Qwen | 2.0B | 40K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-1.7B.md | | LFM2.5-24B-A2B | Liquid AI | 24B | 125K | Custom license | https://sference.com/models/LiquidAI/LFM2.5-24B-A2B.md | | Qwen3-30B-A3B | Qwen | 31B | 40K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-30B-A3B.md | | SmolLM3-3B | Hugging Face | 3.1B | 64K | Apache 2.0 | https://sference.com/models/HuggingFaceTB/SmolLM3-3B.md | | Qwen3-235B-A22B | Qwen | 235B | 40K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-235B-A22B.md | | DeepSeek-V3.2 | DeepSeek | 685B | 160K | MIT | https://sference.com/models/deepseek-ai/DeepSeek-V3.2.md | | Qwen3.5-122B-A10B | Qwen | 125B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3.5-122B-A10B.md | | MiniMax-M2.7 | MiniMax | 229B | 200K | Custom license | https://sference.com/models/MiniMaxAI/MiniMax-M2.7.md | | Qwen3.5-2B | Qwen | 2.3B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3.5-2B.md | | Kimi-K2-Instruct | Moonshot AI | 1.03T | 128K | Modified MIT | https://sference.com/models/moonshotai/Kimi-K2-Instruct.md | | GLM-4.6 | Z.ai | 357B | 200K | MIT | https://sference.com/models/zai-org/GLM-4.6.md | | MiniMax-M2 | MiniMax | 229B | 200K | Modified MIT | https://sference.com/models/MiniMaxAI/MiniMax-M2.md | | Kimi-K2-Thinking | Moonshot AI | 1.03T | 256K | Modified MIT | https://sference.com/models/moonshotai/Kimi-K2-Thinking.md | | GLM-4.5 | Z.ai | 358B | 128K | MIT | https://sference.com/models/zai-org/GLM-4.5.md | | Inkling-Small | Thinking Machines | 266B | 1M | Apache 2.0 | https://sference.com/models/thinkingmachines/Inkling-Small.md | | DeepSeek-V3-0324 | DeepSeek | 685B | 160K | MIT | https://sference.com/models/deepseek-ai/DeepSeek-V3-0324.md | | Qwen3-Next-80B-A3B-Instruct | Qwen | 81B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-Next-80B-A3B-Instruct.md | | gemma-3-270m-it | Google | 268M | — | Gemma Terms of Use | https://sference.com/models/google/gemma-3-270m-it.md | | Qwen3-30B-A3B-Instruct-2507 | Qwen | 31B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-30B-A3B-Instruct-2507.md | | NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | NVIDIA | 32B | 256K | NVIDIA Nemotron Open Model License | https://sference.com/models/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.md | | Step-3.5-Flash | StepFun | 199B | 256K | Apache 2.0 | https://sference.com/models/stepfun-ai/Step-3.5-Flash.md | | Qwen3.5-397B-A17B | Qwen | 403B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3.5-397B-A17B.md | | QwQ-32B | Qwen | 33B | 40K | Apache 2.0 | https://sference.com/models/Qwen/QwQ-32B.md | | Ling-3.0-tiny | inclusionAI | 7.9B | 128K | MIT | https://sference.com/models/inclusionAI/Ling-3.0-tiny.md | | MiniMax-M2.1 | MiniMax | 229B | 200K | Modified MIT | https://sference.com/models/MiniMaxAI/MiniMax-M2.1.md | | Qwen3-32B | Qwen | 33B | 128K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-32B.md | | NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | NVIDIA | 32B | 1M | OpenMDW 1.1 | https://sference.com/models/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16.md | | Mistral-Small-3.2-24B-Instruct-2506 | Mistral AI | 24B | 250K | Apache 2.0 | https://sference.com/models/mistralai/Mistral-Small-3.2-24B-Instruct-2506.md | | gemma-3-12b-it | Google | 12B | 128K | Gemma Terms of Use | https://sference.com/models/google/gemma-3-12b-it.md | | Qwen3-4B-Thinking-2507 | Qwen | 4.0B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-4B-Thinking-2507.md | | Beam-1.0-501B-A23B | Reflection AI | 501B | 1M | Apache 2.0 | https://sference.com/models/reflection/Beam-1.0-501B-A23B.md | | GLM-4.5-Air | Z.ai | 110B | 128K | MIT | https://sference.com/models/zai-org/GLM-4.5-Air.md | | DeepSeek-R1-0528 | DeepSeek | 685B | 160K | MIT | https://sference.com/models/deepseek-ai/DeepSeek-R1-0528.md | | Llama-4-Scout-17B-16E-Instruct | Meta Llama | 109B | 1.3M | Llama 4 Community License | https://sference.com/models/meta-llama/Llama-4-Scout-17B-16E-Instruct.md | | DeepSeek-R1-0528-Qwen3-8B | DeepSeek | 8.2B | 128K | MIT | https://sference.com/models/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B.md | | Mistral-Small-4-119B-2603 | Mistral AI | 119B | 256K | Apache 2.0 | https://sference.com/models/mistralai/Mistral-Small-4-119B-2603.md | | DeepSeek-V4-Pro-0813 | DeepSeek | 1.65T | 1M | MIT | https://sference.com/models/deepseek-ai/DeepSeek-V4-Pro-0813.md | | Ministral-3-14B-Instruct-2512 | Mistral AI | 14B | 256K | Apache 2.0 | https://sference.com/models/mistralai/Ministral-3-14B-Instruct-2512.md | | Qwen3-235B-A22B-Instruct-2507 | Qwen | 235B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-235B-A22B-Instruct-2507.md | | Kimi-Linear-48B-A3B-Instruct | Moonshot AI | 49B | — | MIT | https://sference.com/models/moonshotai/Kimi-Linear-48B-A3B-Instruct.md | | medgemma-27b-it | Google | 27B | — | Custom license | https://sference.com/models/google/medgemma-27b-it.md | | LFM2.5-8B-A1B | Liquid AI | 8.5B | 125K | Custom license | https://sference.com/models/LiquidAI/LFM2.5-8B-A1B.md | | LFM2.5-1.2B-Instruct | Liquid AI | 1.2B | 125K | Custom license | https://sference.com/models/LiquidAI/LFM2.5-1.2B-Instruct.md | | Solar-Open2-250B | Upstage | 250B | 1M | Custom license | https://sference.com/models/upstage/Solar-Open2-250B.md | | Qwen3-30B-A3B-Thinking-2507 | Qwen | 31B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-30B-A3B-Thinking-2507.md | | DeepSeek-V3.2-Speciale | DeepSeek | 685B | 160K | MIT | https://sference.com/models/deepseek-ai/DeepSeek-V3.2-Speciale.md | | ERNIE-4.5-21B-A3B-Thinking | Baidu | 22B | 128K | Apache 2.0 | https://sference.com/models/baidu/ERNIE-4.5-21B-A3B-Thinking.md | | gemma-3n-E4B-it | Google | 7.8B | — | Gemma Terms of Use | https://sference.com/models/google/gemma-3n-E4B-it.md | | DeepSeek-V3.1 | DeepSeek | 685B | 160K | MIT | https://sference.com/models/deepseek-ai/DeepSeek-V3.1.md | | MiMo-V2.5-Pro | Xiaomi MiMo | 1.02T | 1M | MIT | https://sference.com/models/XiaomiMiMo/MiMo-V2.5-Pro.md | | DeepSeek-Math-V2 | DeepSeek | 685B | 160K | Apache 2.0 | https://sference.com/models/deepseek-ai/DeepSeek-Math-V2.md | | Tongyi-DeepResearch-30B-A3B | Alibaba NLP | 31B | 128K | Apache 2.0 | https://sference.com/models/Alibaba-NLP/Tongyi-DeepResearch-30B-A3B.md | | Qwen3-Next-80B-A3B-Thinking | Qwen | 81B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-Next-80B-A3B-Thinking.md | | Ling-3.0-flash | inclusionAI | 127B | 256K | MIT | https://sference.com/models/inclusionAI/Ling-3.0-flash.md | | NVIDIA-Nemotron-Nano-9B-v2 | NVIDIA | 8.9B | 128K | Custom license | https://sference.com/models/nvidia/NVIDIA-Nemotron-Nano-9B-v2.md | | Apertus-8B-Instruct-2509 | Swiss AI Initiative | 8.1B | 64K | Apache 2.0 | https://sference.com/models/swiss-ai/Apertus-8B-Instruct-2509.md | | DeepSeek-V3.1-Terminus | DeepSeek | 685B | 160K | MIT | https://sference.com/models/deepseek-ai/DeepSeek-V3.1-Terminus.md | | Hunyuan-A13B-Instruct | Tencent | 80B | 128K | Custom license | https://sference.com/models/tencent/Hunyuan-A13B-Instruct.md | | Nemotron-Cascade-2-30B-A3B | NVIDIA | 32B | 256K | Custom license | https://sference.com/models/nvidia/Nemotron-Cascade-2-30B-A3B.md | | Qwen3-235B-A22B-Thinking-2507 | Qwen | 235B | 125K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-235B-A22B-Thinking-2507.md | | MiMo-V2-Flash | Xiaomi MiMo | 310B | 256K | MIT | https://sference.com/models/XiaomiMiMo/MiMo-V2-Flash.md | | Kimi-K2-Instruct-0905 | Moonshot AI | 1.03T | 256K | Modified MIT | https://sference.com/models/moonshotai/Kimi-K2-Instruct-0905.md | | MiMo-V2.5 | Xiaomi MiMo | 311B | 1M | MIT | https://sference.com/models/XiaomiMiMo/MiMo-V2.5.md | | granite-4.2-8b | IBM | 8.8B | 128K | Apache 2.0 | https://sference.com/models/ibm-granite/granite-4.2-8b.md | | Magistral-Small-2509 | Mistral AI | 24B | 128K | Apache 2.0 | https://sference.com/models/mistralai/Magistral-Small-2509.md | | Mistral-Large-3-675B-Instruct-2512 | Mistral AI | — | — | Apache 2.0 | https://sference.com/models/mistralai/Mistral-Large-3-675B-Instruct-2512.md | | Llama-4-Maverick-17B-128E-Instruct | Meta Llama | 402B | 512K | Llama 4 Community License | https://sference.com/models/meta-llama/Llama-4-Maverick-17B-128E-Instruct.md | | Step-3.7-Flash | StepFun | 201B | 256K | Apache 2.0 | https://sference.com/models/stepfun-ai/Step-3.7-Flash.md | | NVIDIA-Nemotron-3-Super-120B-A12B-FP8 | NVIDIA | 124B | 256K | NVIDIA Nemotron Open Model License | https://sference.com/models/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8.md | | Ministral-3-8B-Instruct-2512 | Mistral AI | 8.9B | 256K | Apache 2.0 | https://sference.com/models/mistralai/Ministral-3-8B-Instruct-2512.md | | gemma-3n-E2B-it | Google | 5.4B | — | Gemma Terms of Use | https://sference.com/models/google/gemma-3n-E2B-it.md | | MiniMax-M1-80k | MiniMax | 456B | 9.8M | Apache 2.0 | https://sference.com/models/MiniMaxAI/MiniMax-M1-80k.md | | K-EXAONE-236B-A23B | LG AI Research | 237B | 256K | Custom license | https://sference.com/models/LGAI-EXAONE/K-EXAONE-236B-A23B.md | | LongCat-Flash-Chat | Meituan LongCat | 562B | 128K | MIT | https://sference.com/models/meituan-longcat/LongCat-Flash-Chat.md | | Seed-OSS-36B-Instruct | ByteDance Seed | 36B | 512K | Apache 2.0 | https://sference.com/models/ByteDance-Seed/Seed-OSS-36B-Instruct.md | | Solar-Open-100B | Upstage | 103B | 128K | Custom license | https://sference.com/models/upstage/Solar-Open-100B.md | | Ling-1T | inclusionAI | 1000B | 32K | MIT | https://sference.com/models/inclusionAI/Ling-1T.md | | Ling-2.6-flash | inclusionAI | 107B | 128K | MIT | https://sference.com/models/inclusionAI/Ling-2.6-flash.md | | GLM-4-32B-0414 | Z.ai | 33B | 32K | MIT | https://sference.com/models/zai-org/GLM-4-32B-0414.md | | granite-4.0-h-small | IBM | 32B | 128K | Apache 2.0 | https://sference.com/models/ibm-granite/granite-4.0-h-small.md | | MiniCPM4.1-8B | OpenBMB | 8.2B | 64K | Apache 2.0 | https://sference.com/models/openbmb/MiniCPM4.1-8B.md | | c4ai-command-a-03-2025 | Cohere | 111B | — | CC BY-NC 4.0 | https://sference.com/models/CohereLabs/c4ai-command-a-03-2025.md | | Apertus-70B-Instruct-2509 | Swiss AI Initiative | 71B | 64K | Apache 2.0 | https://sference.com/models/swiss-ai/Apertus-70B-Instruct-2509.md | | LongCat-2.0 | Meituan LongCat | 1.78T | 1M | MIT | https://sference.com/models/meituan-longcat/LongCat-2.0.md | | EuroLLM-22B-Instruct-2512 | EuroLLM | 23B | 32K | Apache 2.0 | https://sference.com/models/utter-project/EuroLLM-22B-Instruct-2512.md | ## Coding | Model | Maker | Params | Context | License | Page | | --- | --- | --- | --- | --- | --- | | Qwen3-Coder-Next | Qwen | 80B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-Coder-Next.md | | Qwen3-Coder-30B-A3B-Instruct | Qwen | 31B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-Coder-30B-A3B-Instruct.md | | Laguna-S-2.1 | poolside | 118B | 1M | OpenMDW 1.1 | https://sference.com/models/poolside/Laguna-S-2.1.md | | Kimi-K2.7-Code | Moonshot AI | 1.03T | 256K | Modified MIT | https://sference.com/models/moonshotai/Kimi-K2.7-Code.md | | Devstral-Small-2-24B-Instruct-2512 | Mistral AI | 24B | 384K | Apache 2.0 | https://sference.com/models/mistralai/Devstral-Small-2-24B-Instruct-2512.md | | Qwen3-Coder-480B-A35B-Instruct | Qwen | 480B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-Coder-480B-A35B-Instruct.md | | KAT-Coder-V2.5-Dev | Kwaipilot | 35B | 256K | Apache 2.0 | https://sference.com/models/Kwaipilot/KAT-Coder-V2.5-Dev.md | | North-Mini-Code-1.0 | Cohere | 30B | 250K | Apache 2.0 | https://sference.com/models/CohereLabs/North-Mini-Code-1.0.md | | Devstral-2-123B-Instruct-2512 | Mistral AI | 125B | 256K | Custom license | https://sference.com/models/mistralai/Devstral-2-123B-Instruct-2512.md | | Laguna-XS-2.1 | poolside | 33B | 256K | OpenMDW 1.1 | https://sference.com/models/poolside/Laguna-XS-2.1.md | | Kimi-Dev-72B | Moonshot AI | 73B | 128K | MIT | https://sference.com/models/moonshotai/Kimi-Dev-72B.md | ## Vision & multimodal | Model | Maker | Params | Context | License | Page | | --- | --- | --- | --- | --- | --- | | Qwen3-VL-8B-Instruct | Qwen | 8.8B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-VL-8B-Instruct.md | | MiniCPM-o-4_5 | OpenBMB | 9.4B | 40K | Apache 2.0 | https://sference.com/models/openbmb/MiniCPM-o-4_5.md | | Qwen2.5-Omni-7B | Qwen | 11B | — | Apache 2.0 | https://sference.com/models/Qwen/Qwen2.5-Omni-7B.md | | MiniCPM-V-4.6 | OpenBMB | 1.3B | 256K | Apache 2.0 | https://sference.com/models/openbmb/MiniCPM-V-4.6.md | | Qwen3-Omni-30B-A3B-Instruct | Qwen | 35B | — | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-Omni-30B-A3B-Instruct.md | | Qwen3-VL-30B-A3B-Instruct | Qwen | 31B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-VL-30B-A3B-Instruct.md | | Phi-4-multimodal-instruct | Microsoft | 5.6B | 128K | MIT | https://sference.com/models/microsoft/Phi-4-multimodal-instruct.md | | Qwen3-VL-4B-Instruct | Qwen | 4.4B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-VL-4B-Instruct.md | | Qwen2.5-VL-72B-Instruct | Qwen | 73B | 125K | Custom license | https://sference.com/models/Qwen/Qwen2.5-VL-72B-Instruct.md | | MiniCPM-V-4.7-35B-A3B | OpenBMB | 35B | 256K | Apache 2.0 | https://sference.com/models/openbmb/MiniCPM-V-4.7-35B-A3B.md | | Qwen3-VL-2B-Instruct | Qwen | 2.1B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-VL-2B-Instruct.md | | Qwen2.5-VL-32B-Instruct | Qwen | 33B | 125K | Apache 2.0 | https://sference.com/models/Qwen/Qwen2.5-VL-32B-Instruct.md | | Qwen3-VL-235B-A22B-Instruct | Qwen | 236B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-VL-235B-A22B-Instruct.md | | moondream3-preview | Moondream | 9.3B | 31K | Custom license | https://sference.com/models/moondream/moondream3-preview.md | | GLM-4.5V | Z.ai | 108B | 64K | MIT | https://sference.com/models/zai-org/GLM-4.5V.md | | Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 | NVIDIA | 33B | 250K | NVIDIA Open Model License | https://sference.com/models/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16.md | | UI-TARS-1.5-7B | ByteDance Seed | 8.3B | 125K | Apache 2.0 | https://sference.com/models/ByteDance-Seed/UI-TARS-1.5-7B.md | | Qwen3-VL-235B-A22B-Thinking | Qwen | 236B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-VL-235B-A22B-Thinking.md | | GLM-4.1V-9B-Thinking | Z.ai | 10B | 64K | MIT | https://sference.com/models/zai-org/GLM-4.1V-9B-Thinking.md | | Fara-7B | Microsoft | 8.3B | 125K | MIT | https://sference.com/models/microsoft/Fara-7B.md | | GLM-4.6V-Flash | Z.ai | 10B | 128K | MIT | https://sference.com/models/zai-org/GLM-4.6V-Flash.md | | LFM2.5-VL-1.6B | Liquid AI | 1.6B | 125K | Custom license | https://sference.com/models/LiquidAI/LFM2.5-VL-1.6B.md | | SmolVLM2-2.2B-Instruct | Hugging Face | 2.2B | 8K | Apache 2.0 | https://sference.com/models/HuggingFaceTB/SmolVLM2-2.2B-Instruct.md | | Step3-VL-10B | StepFun | 10B | 64K | Apache 2.0 | https://sference.com/models/stepfun-ai/Step3-VL-10B.md | | ERNIE-4.5-VL-28B-A3B-Thinking | Baidu | 30B | 128K | Apache 2.0 | https://sference.com/models/baidu/ERNIE-4.5-VL-28B-A3B-Thinking.md | | Ling-3.0-flash-VL | inclusionAI | 125B | 128K | MIT | https://sference.com/models/inclusionAI/Ling-3.0-flash-VL.md | | moondream3.1-9B-A2B | Moondream | 9.3B | 31K | Custom license | https://sference.com/models/moondream/moondream3.1-9B-A2B.md | | Apriel-1.6-15b-Thinker | ServiceNow | 15B | 256K | MIT | https://sference.com/models/ServiceNow-AI/Apriel-1.6-15b-Thinker.md | | GLM-4.6V | Z.ai | 108B | 128K | MIT | https://sference.com/models/zai-org/GLM-4.6V.md | | Kimi-VL-A3B-Thinking-2506 | Moonshot AI | 16B | 128K | MIT | https://sference.com/models/moonshotai/Kimi-VL-A3B-Thinking-2506.md | | Intern-S1 | InternLM | 241B | 64K | Apache 2.0 | https://sference.com/models/internlm/Intern-S1.md | | aya-vision-8b | Cohere | 8.6B | — | CC BY-NC 4.0 | https://sference.com/models/CohereLabs/aya-vision-8b.md | ## OCR & documents | Model | Maker | Params | Context | License | Page | | --- | --- | --- | --- | --- | --- | | Unlimited-OCR | Baidu | 3.3B | 32K | MIT | https://sference.com/models/baidu/Unlimited-OCR.md | | DeepSeek-OCR | DeepSeek | 3.3B | 8K | MIT | https://sference.com/models/deepseek-ai/DeepSeek-OCR.md | | chandra-ocr-2 | Datalab | 5.3B | 256K | Custom license | https://sference.com/models/datalab-to/chandra-ocr-2.md | | LightOnOCR-2-1B | LightOn | 1.0B | 16K | Apache 2.0 | https://sference.com/models/lightonai/LightOnOCR-2-1B.md | | granite-docling-258M | IBM | 258M | 8K | Apache 2.0 | https://sference.com/models/ibm-granite/granite-docling-258M.md | | DeepSeek-OCR-2 | DeepSeek | 3.4B | 8K | Apache 2.0 | https://sference.com/models/deepseek-ai/DeepSeek-OCR-2.md | | HunyuanOCR | Tencent | 1.1B | 128K | Custom license | https://sference.com/models/tencent/HunyuanOCR.md | | PaddleOCR-VL | PaddlePaddle | 959M | 128K | Apache 2.0 | https://sference.com/models/PaddlePaddle/PaddleOCR-VL.md | | dots.ocr | dots.ocr | 3.0B | 128K | MIT | https://sference.com/models/dots-studio/dots.ocr.md | | Qianfan-OCR | Baidu | 4.7B | 32K | Apache 2.0 | https://sference.com/models/baidu/Qianfan-OCR.md | | PaddleOCR-VL-1.6 | PaddlePaddle | 959M | 128K | Apache 2.0 | https://sference.com/models/PaddlePaddle/PaddleOCR-VL-1.6.md | | Nanonets-OCR2-3B | Nanonets | 3.8B | 125K | Custom license | https://sference.com/models/nanonets/Nanonets-OCR2-3B.md | | RolmOCR | Reducto | 8.3B | 125K | Apache 2.0 | https://sference.com/models/reducto/RolmOCR.md | | MinerU2.5-2509-1.2B | OpenDataLab | 1.2B | 16K | Custom license | https://sference.com/models/opendatalab/MinerU2.5-2509-1.2B.md | | olmOCR-2-7B-1025 | Ai2 | 8.3B | 125K | Apache 2.0 | https://sference.com/models/allenai/olmOCR-2-7B-1025.md | ## Embeddings | Model | Maker | Params | Context | License | Page | | --- | --- | --- | --- | --- | --- | | bge-m3 | BAAI | — | 8K | MIT | https://sference.com/models/BAAI/bge-m3.md | | embeddinggemma-2 | Google | 744M | 256K | Apache 2.0 | https://sference.com/models/google/embeddinggemma-2.md | | embeddinggemma-300m | Google | 303M | — | Gemma Terms of Use | https://sference.com/models/google/embeddinggemma-300m.md | | Qwen3-Embedding-0.6B | Qwen | 596M | 32K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-Embedding-0.6B.md | | Qwen3-Embedding-8B | Qwen | 7.6B | 40K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-Embedding-8B.md | | jina-embeddings-v3 | Jina AI | 572M | 8K | CC BY-NC 4.0 | https://sference.com/models/jinaai/jina-embeddings-v3.md | | Qwen3-VL-Embedding-8B | Qwen | 8.1B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-VL-Embedding-8B.md | | Qwen3-VL-Embedding-2B | Qwen | 2.1B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-VL-Embedding-2B.md | | multilingual-e5-large-instruct | intfloat | 560M | 1K | MIT | https://sference.com/models/intfloat/multilingual-e5-large-instruct.md | | jina-embeddings-v5-omni-small | Jina AI | 1.6B | 32K | CC BY-NC 4.0 | https://sference.com/models/jinaai/jina-embeddings-v5-omni-small.md | | nomic-embed-text-v2-moe | Nomic | 475M | — | Apache 2.0 | https://sference.com/models/nomic-ai/nomic-embed-text-v2-moe.md | | gte-multilingual-base | Alibaba NLP | 305M | 8K | Apache 2.0 | https://sference.com/models/Alibaba-NLP/gte-multilingual-base.md | | Nemotron-3-Embed-1B-BF16 | NVIDIA | 1.1B | 256K | OpenMDW 1.1 | https://sference.com/models/nvidia/Nemotron-3-Embed-1B-BF16.md | | snowflake-arctic-embed-l-v2.0 | Snowflake | 568M | 8K | Apache 2.0 | https://sference.com/models/Snowflake/snowflake-arctic-embed-l-v2.0.md | | Qwen3-Embedding-4B | Qwen | 4.0B | 40K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-Embedding-4B.md | | harrier-oss-v1-0.6b | Microsoft | 596M | 32K | MIT | https://sference.com/models/microsoft/harrier-oss-v1-0.6b.md | | granite-embedding-small-english-r2 | IBM | 48M | 8K | Apache 2.0 | https://sference.com/models/ibm-granite/granite-embedding-small-english-r2.md | | Nemotron-3-Embed-8B-BF16 | NVIDIA | 8.0B | 256K | OpenMDW 1.1 | https://sference.com/models/nvidia/Nemotron-3-Embed-8B-BF16.md | | pplx-embed-v1-0.6b | Perplexity | 596M | 32K | MIT | https://sference.com/models/perplexity-ai/pplx-embed-v1-0.6b.md | | jina-embeddings-v4 | Jina AI | 3.8B | 125K | Custom license | https://sference.com/models/jinaai/jina-embeddings-v4.md | | llama-nemotron-embed-1b-v2 | NVIDIA | 1.2B | 128K | Custom license | https://sference.com/models/nvidia/llama-nemotron-embed-1b-v2.md | | nomic-embed-code | Nomic | 7.1B | 32K | Apache 2.0 | https://sference.com/models/nomic-ai/nomic-embed-code.md | | gte-modernbert-base | Alibaba NLP | 149M | 8K | Apache 2.0 | https://sference.com/models/Alibaba-NLP/gte-modernbert-base.md | | granite-embedding-english-r2 | IBM | 149M | 8K | Apache 2.0 | https://sference.com/models/ibm-granite/granite-embedding-english-r2.md | ## Rerankers | Model | Maker | Params | Context | License | Page | | --- | --- | --- | --- | --- | --- | | bge-reranker-v2-m3 | BAAI | 568M | 8K | Apache 2.0 | https://sference.com/models/BAAI/bge-reranker-v2-m3.md | | Qwen3-Reranker-0.6B | Qwen | 596M | 40K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-Reranker-0.6B.md | | Qwen3-Reranker-4B | Qwen | 4.0B | 40K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-Reranker-4B.md | | Qwen3-VL-Reranker-2B | Qwen | 2.1B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-VL-Reranker-2B.md | | Qwen3-Reranker-8B | Qwen | 8.2B | 40K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-Reranker-8B.md | | gte-reranker-modernbert-base | Alibaba NLP | 150M | 8K | Apache 2.0 | https://sference.com/models/Alibaba-NLP/gte-reranker-modernbert-base.md | | jina-reranker-v3 | Jina AI | 597M | 128K | CC BY-NC 4.0 | https://sference.com/models/jinaai/jina-reranker-v3.md | | llama-nemotron-rerank-1b-v2 | NVIDIA | 1.2B | 128K | OpenMDW 1.1 | https://sference.com/models/nvidia/llama-nemotron-rerank-1b-v2.md | | Qwen3-VL-Reranker-8B | Qwen | 8.8B | 256K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-VL-Reranker-8B.md | | bge-reranker-v2-gemma | BAAI | 2.5B | 8K | Apache 2.0 | https://sference.com/models/BAAI/bge-reranker-v2-gemma.md | | zerank-2-reranker | ZeroEntropy | 4.0B | 40K | Apache 2.0 | https://sference.com/models/zeroentropy/zerank-2-reranker.md | | jina-reranker-m0 | Jina AI | 2.4B | 32K | CC BY-NC 4.0 | https://sference.com/models/jinaai/jina-reranker-m0.md | | mxbai-rerank-large-v2 | Mixedbread | 1.5B | 32K | Apache 2.0 | https://sference.com/models/mixedbread-ai/mxbai-rerank-large-v2.md | ## Speech recognition | Model | Maker | Params | Context | License | Page | | --- | --- | --- | --- | --- | --- | | speaker-diarization-community-1 | pyannote | — | — | CC BY 4.0 | https://sference.com/models/pyannote/speaker-diarization-community-1.md | | whisper-large-v3 | OpenAI | 1.5B | — | Apache 2.0 | https://sference.com/models/openai/whisper-large-v3.md | | whisper-large-v3-turbo | OpenAI | 809M | — | MIT | https://sference.com/models/openai/whisper-large-v3-turbo.md | | Qwen3-ASR-1.7B | Qwen | 2.3B | — | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-ASR-1.7B.md | | nemotron-3.5-asr-streaming-0.6b | NVIDIA | 638M | — | OpenMDW 1.1 | https://sference.com/models/nvidia/nemotron-3.5-asr-streaming-0.6b.md | | parakeet-tdt-0.6b-v3 | NVIDIA | 627M | — | CC BY 4.0 | https://sference.com/models/nvidia/parakeet-tdt-0.6b-v3.md | | parakeet-tdt-0.6b-v2 | NVIDIA | — | — | CC BY 4.0 | https://sference.com/models/nvidia/parakeet-tdt-0.6b-v2.md | | Voxtral-Mini-4B-Realtime-2602 | Mistral AI | 4.4B | 128K | Apache 2.0 | https://sference.com/models/mistralai/Voxtral-Mini-4B-Realtime-2602.md | | VibeVoice-ASR | Microsoft | 8.7B | — | MIT | https://sference.com/models/microsoft/VibeVoice-ASR.md | | cohere-transcribe-03-2026 | Cohere | 2.1B | — | Apache 2.0 | https://sference.com/models/CohereLabs/cohere-transcribe-03-2026.md | | Qwen3-ASR-0.6B | Qwen | 938M | — | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-ASR-0.6B.md | | Voxtral-Mini-3B-2507 | Mistral AI | 4.7B | 128K | Apache 2.0 | https://sference.com/models/mistralai/Voxtral-Mini-3B-2507.md | | Voxtral-Small-24B-2507 | Mistral AI | 24B | 32K | Apache 2.0 | https://sference.com/models/mistralai/Voxtral-Small-24B-2507.md | | canary-1b-v2 | NVIDIA | 979M | — | CC BY 4.0 | https://sference.com/models/nvidia/canary-1b-v2.md | | canary-qwen-2.5b | NVIDIA | 2.6B | — | CC BY 4.0 | https://sference.com/models/nvidia/canary-qwen-2.5b.md | | GLM-ASR-Nano-2512 | Z.ai | 2.3B | 8K | MIT | https://sference.com/models/zai-org/GLM-ASR-Nano-2512.md | ## Text-to-speech | Model | Maker | Params | Context | License | Page | | --- | --- | --- | --- | --- | --- | | Kokoro-82M | hexgrad | — | — | Apache 2.0 | https://sference.com/models/hexgrad/Kokoro-82M.md | | Qwen3-TTS-12Hz-1.7B-CustomVoice | Qwen | 1.9B | — | Apache 2.0 | https://sference.com/models/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice.md | | VoxCPM2 | OpenBMB | 2.3B | — | Apache 2.0 | https://sference.com/models/openbmb/VoxCPM2.md | | chatterbox | Resemble AI | — | — | MIT | https://sference.com/models/ResembleAI/chatterbox.md | | s2-pro | Fish Audio | 4.6B | 32K | Custom license | https://sference.com/models/fishaudio/s2-pro.md | | VibeVoice-1.5B | Microsoft | 2.7B | — | MIT | https://sference.com/models/microsoft/VibeVoice-1.5B.md | | csm-1b | Sesame | 1.6B | — | Apache 2.0 | https://sference.com/models/sesame/csm-1b.md | | Voxtral-4B-TTS-2603 | Mistral AI | — | — | CC BY-NC 4.0 | https://sference.com/models/mistralai/Voxtral-4B-TTS-2603.md | | Fun-CosyVoice3-0.5B-2512 | FunAudioLLM | — | — | Apache 2.0 | https://sference.com/models/FunAudioLLM/Fun-CosyVoice3-0.5B-2512.md | | Dia-1.6B | Nari Labs | 1.6B | — | Apache 2.0 | https://sference.com/models/nari-labs/Dia-1.6B.md | | VibeVoice-Realtime-0.5B | Microsoft | 1.0B | — | MIT | https://sference.com/models/microsoft/VibeVoice-Realtime-0.5B.md | | orpheus-3b-0.1-ft | Canopy Labs | 3.8B | — | Apache 2.0 | https://sference.com/models/canopylabs/orpheus-3b-0.1-ft.md | | IndexTTS-2 | IndexTeam | — | — | Custom license | https://sference.com/models/IndexTeam/IndexTTS-2.md | | chatterbox-turbo | Resemble AI | — | — | MIT | https://sference.com/models/ResembleAI/chatterbox-turbo.md | | tts-1.6b-en_fr | Kyutai | — | — | CC BY 4.0 | https://sference.com/models/kyutai/tts-1.6b-en_fr.md | ## Translation | Model | Maker | Params | Context | License | Page | | --- | --- | --- | --- | --- | --- | | Hy-MT2-1.8B | Tencent | 2.0B | 8K | Apache 2.0 | https://sference.com/models/tencent/Hy-MT2-1.8B.md | | Hy-MT2-30B-A3B | Tencent | 30B | 8K | Apache 2.0 | https://sference.com/models/tencent/Hy-MT2-30B-A3B.md | | Hunyuan-MT-7B | Tencent | 8.0B | 32K | Custom license | https://sference.com/models/tencent/Hunyuan-MT-7B.md | | translategemma-12b-it | Google | 12B | — | Gemma Terms of Use | https://sference.com/models/google/translategemma-12b-it.md | | translategemma-27b-it | Google | 27B | — | Gemma Terms of Use | https://sference.com/models/google/translategemma-27b-it.md | | Hy-MT2-7B | Tencent | 8.0B | 8K | Apache 2.0 | https://sference.com/models/tencent/Hy-MT2-7B.md | | Seed-X-PPO-7B | ByteDance Seed | 7.5B | 32K | Custom license | https://sference.com/models/ByteDance-Seed/Seed-X-PPO-7B.md | ## Safety & moderation | Model | Maker | Params | Context | License | Page | | --- | --- | --- | --- | --- | --- | | Llama-Prompt-Guard-2-86M | Meta Llama | 279M | — | Llama 4 Community License | https://sference.com/models/meta-llama/Llama-Prompt-Guard-2-86M.md | | Qwen3Guard-Gen-8B | Qwen | 8.2B | 32K | Apache 2.0 | https://sference.com/models/Qwen/Qwen3Guard-Gen-8B.md | | gpt-oss-safeguard-20b | OpenAI | 22B | 128K | Apache 2.0 | https://sference.com/models/openai/gpt-oss-safeguard-20b.md | | Nemotron-3.5-Content-Safety | NVIDIA | 4.3B | 128K | OpenMDW | https://sference.com/models/nvidia/Nemotron-3.5-Content-Safety.md | | shieldgemma-2-4b-it | Google | 4.3B | — | Gemma Terms of Use | https://sference.com/models/google/shieldgemma-2-4b-it.md | | Llama-Guard-4-12B | Meta Llama | 12B | 160K | Llama 4 Community License | https://sference.com/models/meta-llama/Llama-Guard-4-12B.md | | granite-guardian-3.3-8b | IBM | 8.2B | 128K | Apache 2.0 | https://sference.com/models/ibm-granite/granite-guardian-3.3-8b.md |