Model catalog
License classes are always qualified — never the bare word “open.” Filter state lives in the URL.
Showing 88 models
| Model | Developer | Params (B) | Context | License class | Local |
|---|---|---|---|---|---|
| c4ai-command-a-03-2025 | Cohere Labs | 111.058 | — | research-only | GGUF |
| Claude Fable 5 | Anthropic | — | — | proprietary-api | API |
| Claude Opus 4.8 | Anthropic | — | — | proprietary-api | API |
| Claude Opus 5 | Anthropic | — | — | proprietary-api | API |
| Claude Sonnet 5 | Anthropic | — | — | proprietary-api | API |
| command-a-plus-05-2026-bf16 | Cohere Labs | 218.75 | 200000 | open-permissive | GGUF |
| DeepSeek-R1-0528 | DeepSeek | 684.531 | 163840 | open-permissive | GGUF |
| DeepSeek-R1-Distill-Qwen-32B | DeepSeek | 32.764 | 131072 | open-permissive | GGUF |
| DeepSeek-V3.2 | DeepSeek | 685.397 | 163840 | open-permissive | GGUF |
| DeepSeek-V4-Flash-0731 | DeepSeek | 304.18 | 1048576 | open-permissive | GGUF |
| DeepSeek-V4-Pro | DeepSeek | 1598.84 | 1048576 | open-permissive | GGUF |
| Devstral-Small-2507 | Mistral AI | 23.572 | 131072 | open-permissive | GGUF |
| Falcon-H1-34B-Instruct | Technology Innovation Institute | 33.643 | 262144 | open-restricted | GGUF |
| Falcon-H1-7B-Instruct | Technology Innovation Institute | 7.586 | 262144 | open-restricted | GGUF |
| Gemini 3.1 Pro (preview) | Google DeepMind | — | — | proprietary-api | API |
| Gemini 3.5 Flash | Google DeepMind | — | — | proprietary-api | API |
| Gemini 3.5 Flash Lite | Google DeepMind | — | — | proprietary-api | API |
| Gemini 3.6 Flash | Google DeepMind | — | — | proprietary-api | API |
| gemma-2-9b-it | Google DeepMind | 9.242 | 8192 | open-restricted | GGUF |
| gemma-3-12b-it | Google DeepMind | 12.187 | 131072 | open-restricted | GGUF |
| gemma-3-27b-it | Google DeepMind | 27.432 | 131072 | open-restricted | GGUF |
| gemma-3-4b-it | Google DeepMind | 4.3 | 131072 | open-restricted | GGUF |
| gemma-4-12B-it | Google DeepMind | 11.96 | 262144 | open-permissive | GGUF |
| gemma-4-26B-A4B-it | Google DeepMind | 26.544 | 262144 | open-permissive | GGUF |
| gemma-4-31B-it | Google DeepMind | 31.273 | 262144 | open-permissive | GGUF |
| gemma-4-E4B-it | Google DeepMind | 7.996 | 131072 | open-permissive | GGUF |
| GLM-4.5-Air | Z.ai (Zhipu AI) | 110.469 | 131072 | open-permissive | GGUF |
| GLM-4.7 | Z.ai (Zhipu AI) | 358.338 | 202752 | open-permissive | GGUF |
| GLM-4.7-Flash | Z.ai (Zhipu AI) | 31.221 | 202752 | open-permissive | GGUF |
| GLM-5.1 | Z.ai (Zhipu AI) | 753.864 | 202752 | open-permissive | GGUF |
| GLM-5.2 | Z.ai (Zhipu AI) | 753.33 | 1048576 | open-permissive | GGUF |
| GPT-5.3 Codex | OpenAI | — | — | proprietary-api | API |
| GPT-5.4 | OpenAI | — | — | proprietary-api | API |
| GPT-5.4 mini | OpenAI | — | — | proprietary-api | API |
| GPT-5.4 nano | OpenAI | — | — | proprietary-api | API |
| GPT-5.5 | OpenAI | — | — | proprietary-api | API |
| GPT-5.6 Luna | OpenAI | — | — | proprietary-api | API |
| GPT-5.6 Sol | OpenAI | — | — | proprietary-api | API |
| GPT-5.6 Terra | OpenAI | — | — | proprietary-api | API |
| gpt-oss-120b | OpenAI | 116.829 | 131072 | open-permissive | GGUF |
| gpt-oss-20b | OpenAI | 21.512 | 131072 | open-permissive | GGUF |
| granite-4.1-30b | IBM | 28.866 | 131072 | open-permissive | GGUF |
| granite-4.1-3b | IBM | 3.403 | 131072 | open-permissive | GGUF |
| Grok 4.3 | xAI | — | — | proprietary-api | API |
| Grok 4.5 | xAI | — | — | proprietary-api | API |
| Kimi-K2.6 | Moonshot AI | 1026.879 | 262144 | open-restricted | GGUF |
| Kimi-K2.7-Code | Moonshot AI | 1026.879 | 262144 | open-restricted | GGUF |
| Kimi-K3 | Moonshot AI | 2779.932 | 1048576 | open-restricted | GGUF |
| Kimi-Linear-48B-A3B-Instruct | Moonshot AI | 49.123 | — | open-permissive | GGUF |
| Llama-3.1-70B-Instruct | Meta AI | 70.554 | 131072 | open-restricted | GGUF |
| Llama-3.1-8B-Instruct | Meta AI | 8.03 | 131072 | open-restricted | GGUF |
| Llama-3.2-3B-Instruct | Meta AI | 3.213 | 131072 | open-restricted | GGUF |
| Llama-3.3-70B-Instruct | Meta AI | 70.554 | 131072 | open-restricted | GGUF |
| Llama-4-Maverick-17B-128E-Instruct | Meta AI | 401.584 | 1048576 | open-restricted | GGUF |
| Llama-4-Scout-17B-16E-Instruct | Meta AI | 108.642 | 10485760 | open-restricted | GGUF |
| Magistral-Small-2509 | Mistral AI | 24.011 | 131072 | open-permissive | GGUF |
| MiniMax-M2.5 | MiniMax | 228.704 | 196608 | open-restricted | GGUF |
| MiniMax-M2.7 | MiniMax | 228.704 | 204800 | open-restricted | GGUF |
| MiniMax-M3 | MiniMax | 427.04 | 1048576 | open-restricted | GGUF |
| Mistral-Nemo-Instruct-2407 | Mistral AI | 12.248 | 131072 | open-permissive | GGUF |
| Mistral-Small-3.2-24B-Instruct-2506 | Mistral AI | 24.011 | 131072 | open-permissive | GGUF |
| NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | NVIDIA | 31.578 | 262144 | open-restricted | GGUF |
| NVIDIA-Nemotron-3-Super-120B-A12B-BF16 | NVIDIA | 123.611 | 262144 | open-restricted | GGUF |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | NVIDIA | 560.525 | 262144 | open-permissive | GGUF |
| NVIDIA-Nemotron-Nano-9B-v2 | NVIDIA | 8.888 | 131072 | open-restricted | GGUF |
| Olmo-3-7B-Instruct | Allen Institute for AI | 7.298 | 65536 | open-permissive | GGUF |
| Olmo-3.1-32B-Instruct | Allen Institute for AI | 32.234 | 65536 | open-permissive | GGUF |
| phi-4 | Microsoft | 14.66 | 16384 | open-permissive | GGUF |
| Phi-4-mini-instruct | Microsoft | 3.836 | 131072 | open-permissive | GGUF |
| Qwen2.5-72B-Instruct | Alibaba (Qwen team) | 72.706 | 32768 | open-restricted | GGUF |
| Qwen2.5-Coder-32B-Instruct | Alibaba (Qwen team) | 32.764 | 32768 | open-permissive | GGUF |
| Qwen3-14B | Alibaba (Qwen team) | 14.768 | 40960 | open-permissive | GGUF |
| Qwen3-235B-A22B-Instruct-2507 | Alibaba (Qwen team) | 235.094 | 262144 | open-permissive | GGUF |
| Qwen3-30B-A3B-Instruct-2507 | Alibaba (Qwen team) | 30.532 | 262144 | open-permissive | GGUF |
| Qwen3-32B | Alibaba (Qwen team) | 32.762 | 40960 | open-permissive | GGUF |
| Qwen3-4B-Instruct-2507 | Alibaba (Qwen team) | 4.022 | 262144 | open-permissive | GGUF |
| Qwen3-8B | Alibaba (Qwen team) | 8.191 | 40960 | open-permissive | GGUF |
| Qwen3.5-122B-A10B | Alibaba (Qwen team) | 125.086 | 262144 | open-permissive | GGUF |
| Qwen3.5-27B | Alibaba (Qwen team) | 27.781 | 262144 | open-permissive | GGUF |
| Qwen3.5-2B | Alibaba (Qwen team) | 2.274 | 262144 | open-permissive | GGUF |
| Qwen3.5-397B-A17B | Alibaba (Qwen team) | 403.398 | 262144 | open-permissive | GGUF |
| Qwen3.5-4B | Alibaba (Qwen team) | 4.66 | 262144 | open-permissive | GGUF |
| Qwen3.5-9B | Alibaba (Qwen team) | 9.653 | 262144 | open-permissive | GGUF |
| Qwen3.6-27B | Alibaba (Qwen team) | 27.781 | 262144 | open-permissive | GGUF |
| Qwen3.6-35B-A3B | Alibaba (Qwen team) | 35.952 | 262144 | open-permissive | GGUF |
| Qwen3.7-Max | Alibaba (Qwen team) | — | — | proprietary-api | API |
| Qwen3.8-Max | Alibaba (Qwen team) | — | — | proprietary-api | API |
| SmolLM3-3B | Hugging Face | 3.075 | 65536 | open-permissive | GGUF |