Browse All Models
Explore all 253 models in our catalog. Filter by family, architecture, or size. Click any model to see detailed specs, GPU requirements, and pricing.
| Name ▲ | Family | Params | Architecture | Context | Quality |
|---|---|---|---|---|---|
| MiniLM | 23M | dense | 256 | 50.0 | |
| Nova | 12B | dense | 300K | 50.0 | |
| Nova | 50B | dense | 300K | 50.0 | |
| Aya | 35B | dense | 131K | 50.0 | |
| Aya | 8B | dense | 8K | 50.0 | |
| Baichuan 2 | 13B | dense | 4K | 50.0 | |
| Baichuan 2 | 7B | dense | 4K | 50.0 | |
| BGE | 110M | dense | 512 | 50.0 | |
| BGE | 335M | dense | 512 | 50.0 | |
| BGE | 568M | dense | 8K | 50.0 | |
| BGE | 33M | dense | 512 | 50.0 | |
| BioMistral | 7.2B | dense | 33K | 50.0 | |
| BTLM | 3B | dense | 8K | 50.0 | |
| Canary | 1B | dense | 4K | 50.0 | |
| Cerebras GPT | 13B | dense | 2K | 50.0 | |
| ChatGLM3 | 6B | dense | 131K | 50.0 | |
| ChatGLM | 9.4B | dense | 131K | 50.0 | |
| Claude | 175B | dense | 200K | 88.0 | |
| Claude | 70B | dense | 200K | 78.0 | |
| Claude | 20B | dense | 200K | 77.0 | |
| Claude | 200B | dense | 200K | 94.0 | |
| Claude | 70B | dense | 200K | 90.0 | |
| Code Llama | 13B | dense | 16K | 44.0 | |
| Code Llama | 34B | dense | 100K | 55.0 | |
| Code Llama | 70B | dense | 16K | 60.0 | |
| Code Llama | 7B | dense | 16K | 39.0 | |
| Gemma | 8.5B | dense | 8K | 52.0 | |
| CodeGen2 | 16B | dense | 2K | 50.0 | |
| Codestral | 22B | dense | 33K | 63.0 | |
| Codestral | 7.3B | hybrid | 262K | 50.0 | |
| CogVLM2 | 19B | dense | 8K | 50.0 | |
| Embed | 500M | dense | 512 | 50.0 | |
| Command | 111B | dense | 256K | 81.0 | |
| Command R | 35B | dense | 131K | 68.0 | |
| Command R | 35B | dense | 128K | 50.0 | |
| Command R | 7B | dense | 131K | 50.0 | |
| Command R | 104B | dense | 131K | 78.0 | |
| DALL-E | 3.5B | dense | 4K | 50.0 | |
| DBRX | 132B (36B active) | moe | 33K | 50.0 | |
| DBRX | 132B (36B active) | moe | 33K | 50.0 | |
| DeepSeek Coder | 33B | dense | 16K | 50.0 | |
| DeepSeek Coder | 6.7B | dense | 16K | 50.0 | |
| DeepSeek Coder V2 | 236B (21B active) | moe | 131K | 50.0 | |
| DeepSeek LLM | 67B | dense | 4K | 66.0 | |
| DeepSeek Math | 7.24B | dense | 4K | 50.0 | |
| DeepSeek MoE | 16.4B (2.8B active) | moe | 4K | 50.0 | |
| DeepSeek R1 | 671B (37B active) | moe | 131K | 92.0 | |
| DeepSeek R1 | 1.5B | dense | 131K | 42.0 | |
| DeepSeek R1 | 14.8B | dense | 131K | 50.0 | |
| DeepSeek R1 | 32.8B | dense | 131K | 50.0 | |
| DeepSeek R1 | 70.6B | dense | 131K | 50.0 | |
| DeepSeek R1 | 8B | dense | 131K | 50.0 | |
| DeepSeek V2 | 15.7B (2.4B active) | moe | 33K | 50.0 | |
| DeepSeek V2 | 236B (21B active) | moe | 131K | 78.0 | |
| DeepSeek V3 | 671B (37B active) | moe | 131K | 86.0 | |
| Dolphin | 72B | dense | 33K | 50.0 | |
| E5 | 7.11B | dense | 33K | 50.0 | |
| ELYZA | 13B | dense | 4K | 50.0 | |
| Falcon | 11B | dense | 8K | 50.0 | |
| Falcon | 180B | dense | 2K | 60.0 | |
| Falcon | 40B | dense | 2K | 48.0 | |
| Falcon | 7B | dense | 2K | 37.0 | |
| Falcon Mamba | 7.27B | hybrid | 8K | 50.0 | |
| FinGPT | 7.2B | dense | 4K | 50.0 | |
| Florence | 770M | dense | 2K | 50.0 | |
| FLUX | 12B | dense | 512 | 50.0 | |
| Gemini | 50B (12B active) | moe | 1049K | 75.0 | |
| Gemini | 175B (40B active) | moe | 2097K | 86.0 | |
| Gemini | 50B (15B active) | moe | 1049K | 83.0 | |
| Gemini | 600B (150B active) | moe | 2000K | 88.0 | |
| Gemma | 2.5B | dense | 8K | 50.0 | |
| Gemma 2 | 27B | dense | 8K | 73.0 | |
| Gemma 2 | 2.6B | dense | 8K | 44.0 | |
| Gemma 2 | 9.2B | dense | 8K | 68.0 | |
| Gemma 3 | 12B | dense | 131K | 71.0 | |
| Gemma 3 | 1B | dense | 33K | 35.0 | |
| Gemma 3 | 27B | dense | 131K | 76.0 | |
| Gemma 3 | 2B | dense | 8K | 42.0 | |
| Gemma 3 | 4.3B | dense | 131K | 54.0 | |
| GigaChat | 20B | dense | 8K | 50.0 | |
| GLM-4 | 9.4B | dense | 131K | 50.0 | |
| GPT-3.5 | 20B | dense | 16K | 67.0 | |
| GPT-4 | 200B (50B active) | moe | 128K | 86.0 | |
| GPT | 1500B (300B active) | moe | 128K | 93.0 | |
| GPT-4 | 200B (50B active) | moe | 128K | 91.0 | |
| GPT-4 | 8B | dense | 128K | 80.0 | |
| Grok | 600B (120B active) | moe | 131K | 90.0 | |
| Grok | 314B (50B active) | moe | 131K | 87.0 | |
| GTE | 7.6B | dense | 33K | 50.0 | |
| H2O Danube | 500M | dense | 8K | 50.0 | |
| Llama 3.1 | 70.6B | dense | 131K | 82.0 | |
| Hermes 3 | 70.6B | dense | 131K | 50.0 | |
| Hermes 3 | 8.03B | dense | 131K | 50.0 | |
| Inflection | 100B | dense | 8K | 74.0 | |
| InfoXLM | 550M | dense | 512 | 50.0 | |
| InternLM 2.5 | 19.9B | dense | 262K | 50.0 | |
| InternLM 2.5 | 7.74B | dense | 1049K | 50.0 | |
| InternLM | 20B | dense | 16K | 50.0 | |
| InternVL2 | 26B | dense | 33K | 50.0 | |
| JAIS | 30B | dense | 8K | 50.0 | |
| Jamba | 398B | hybrid | 256K | 50.0 | |
| Jamba | 52B | hybrid | 256K | 50.0 | |
| Jamba | 52B (12B active) | moe | 256K | 66.0 | |
| StableLM | 70B | dense | 8K | 50.0 | |
| Jina Embeddings | 570M | dense | 8K | 50.0 | |
| Kimi | 1000B (32B active) | moe | 131K | 50.0 | |
| KULLM | 12.8B | dense | 4K | 50.0 | |
| Llama 2 | 13B | dense | 4K | 47.0 | |
| Llama 2 | 70B | dense | 4K | 62.0 | |
| Llama 2 | 7B | dense | 4K | 40.0 | |
| Llama 3 | 70.6B | dense | 8K | 80.0 | |
| Llama 3 | 70.6B | dense | 1049K | 50.0 | |
| Llama 3 | 8B | dense | 8K | 63.0 | |
| Llama 3.1 | 405B | dense | 131K | 88.0 | |
| Llama 3.1 | 70.6B | dense | 131K | 82.0 | |
| Llama 3.1 | 70.6B | dense | 131K | 50.0 | |
| Llama 3.1 | 8.03B | dense | 131K | 65.0 | |
| Llama 3.1 | 51B | dense | 131K | 78.0 | |
| Llama 3.1 | 70.6B | dense | 131K | 83.0 | |
| Llama 3.1 | 70.6B | dense | 131K | 80.0 | |
| Llama 3.2 | 11B | dense | 131K | 50.0 | |
| Llama 3.2 | 1.24B | dense | 131K | 38.0 | |
| Llama 3.2 | 3.21B | dense | 131K | 55.0 | |
| Llama 3.2 | 90B | dense | 131K | 50.0 | |
| Llama 3.2 | 88.8B | dense | 131K | 84.0 | |
| Llama 3.3 | 70.6B | dense | 131K | 84.0 | |
| Llama 3.3 | 8B | dense | 131K | 50.0 | |
| Llama 4 | 2000B (400B active) | moe | 1049K | 93.0 | |
| Llama 4 | 400B (17B active) | moe | 1049K | 89.0 | |
| Llama 4 | 109B (17B active) | moe | 10486K | 76.0 | |
| Llama Guard | 1B | dense | 131K | 50.0 | |
| Llama Guard | 8B | dense | 131K | 50.0 | |
| Marco | 7.6B | dense | 66K | 50.0 | |
| Meditron | 70B | dense | 4K | 50.0 | |
| Megatron-Turing | 530B | dense | 2K | 58.0 | |
| Ministral | 8B | dense | 131K | 50.0 | |
| Nemotron | 4B | dense | 8K | 50.0 | |
| Nemotron | 8B | dense | 8K | 62.0 | |
| Mistral | 7.3B | dense | 33K | 56.0 | |
| Mistral Large | 123B | dense | 131K | 82.0 | |
| Mistral Large | 123B | dense | 131K | 50.0 | |
| Mistral | 70B | dense | 131K | 80.0 | |
| Mistral Nemo | 12B | dense | 131K | 62.0 | |
| Mistral Small | 24B | dense | 33K | 68.0 | |
| Mistral Small | 24B | dense | 131K | 50.0 | |
| Mixtral | 141B (39B active) | moe | 66K | 73.0 | |
| Mixtral | 46.7B (12.9B active) | moe | 33K | 67.0 | |
| Mixtral | 46.7B (12.9B active) | moe | 33K | 69.0 | |
| MPT | 30B | dense | 8K | 48.0 | |
| MPT | 6.7B | dense | 66K | 36.0 | |
| E5 | 560M | dense | 512 | 50.0 | |
| Nekomata | 14B | dense | 4K | 50.0 | |
| Nemotron | 15B | dense | 4K | 72.0 | |
| Nemotron | 340B | dense | 131K | 85.0 | |
| Nemotron | 70.6B | dense | 131K | 83.0 | |
| Nemotron | 4B | dense | 8K | 48.0 | |
| Nomic Embed | 137M | dense | 8K | 50.0 | |
| NV Embed | 7.85B | dense | 33K | 50.0 | |
| NV EmbedQA | 330M | dense | 512 | 50.0 | |
| NV EmbedQA | 7.24B | dense | 33K | 50.0 | |
| NV Retriever | 330M | dense | 512 | 50.0 | |
| o1 | 200B (50B active) | moe | 200K | 95.0 | |
| o1 | 70B | dense | 128K | 86.0 | |
| o3 | 70B | dense | 200K | 89.0 | |
| OctoCoder | 15.5B | dense | 8K | 50.0 | |
| OLMo 2 | 13B | dense | 4K | 50.0 | |
| OLMo 2 | 7B | dense | 4K | 50.0 | |
| OpenELM | 3B | dense | 2K | 50.0 | |
| OpenHermes | 7B | dense | 33K | 50.0 | |
| Orca | 13B | dense | 4K | 50.0 | |
| PaLI-Gemma | 2.9B | dense | 8K | 50.0 | |
| Parakeet | 600M | dense | 4K | 50.0 | |
| Parakeet | 1.1B | dense | 4K | 50.0 | |
| Phi | 1.3B | dense | 2K | 38.0 | |
| Phi | 1.3B | dense | 2K | 50.0 | |
| Phi | 2.7B | dense | 2K | 50.0 | |
| Phi 3 | 14B | dense | 131K | 76.0 | |
| Phi 3 | 3.8B | dense | 131K | 64.0 | |
| Phi 3 | 7B | dense | 131K | 72.0 | |
| Phi | 41.9B (6.6B active) | moe | 131K | 74.0 | |
| Phi 3.5 | 4.2B | dense | 131K | 50.0 | |
| Phi | 3.8B | dense | 131K | 70.0 | |
| Phi | 14.7B | dense | 16K | 83.0 | |
| Pixtral | 12B | dense | 131K | 50.0 | |
| Prometheus | 7.24B | dense | 8K | 50.0 | |
| Qwen 1.5 | 14.3B (2.7B active) | moe | 33K | 50.0 | |
| Qwen 2 | 7.6B | dense | 33K | 50.0 | |
| Qwen 2 VL | 2.2B | dense | 33K | 50.0 | |
| Qwen 2.5 | 500M | dense | 33K | 50.0 | |
| Qwen 2.5 | 1.5B | dense | 33K | 50.0 | |
| Qwen 2.5 | 14.8B | dense | 131K | 76.0 | |
| Qwen 2.5 | 32.5B | dense | 131K | 81.0 | |
| Qwen 2.5 | 3.09B | dense | 33K | 58.0 | |
| Qwen 2.5 | 72.7B | dense | 131K | 84.0 | |
| Qwen 2.5 | 7.6B | dense | 131K | 70.0 | |
| Qwen 2.5 Coder | 1.5B | dense | 33K | 40.0 | |
| Qwen 2.5 Coder | 14.7B | dense | 131K | 50.0 | |
| Qwen 2.5 | 32.5B | dense | 131K | 50.0 | |
| Qwen 2.5 Coder | 3.1B | dense | 33K | 50.0 | |
| Qwen 2.5 Coder | 7.6B | dense | 131K | 50.0 | |
| Qwen 2.5 Math | 72.7B | dense | 4K | 50.0 | |
| Qwen 2.5 Math | 7.6B | dense | 4K | 50.0 | |
| Qwen 2.5 VL | 72.7B | dense | 131K | 50.0 | |
| Qwen 2.5 VL | 7.6B | dense | 131K | 50.0 | |
| Qwen 3 | 600M | dense | 131K | 50.0 | |
| Qwen 3 | 1.7B | dense | 131K | 50.0 | |
| Qwen 3 | 235B (22B active) | moe | 131K | 88.0 | |
| Qwen 3 | 30.5B (3.3B active) | moe | 131K | 70.0 | |
| Qwen 3 | 32.8B | dense | 131K | 80.0 | |
| Qwen 3 | 4B | dense | 131K | 57.0 | |
| Qwen 3 | 8.2B | dense | 131K | 67.0 | |
| RecurrentGemma | 2.7B | dense | 8K | 50.0 | |
| Reka | 70B | dense | 128K | 76.0 | |
| Replit Code | 3.3B | dense | 4K | 50.0 | |
| RWKV | 14.1B | hybrid | 33K | 50.0 | |
| SantaCoder | 1.1B | dense | 2K | 50.0 | |
| SaulLM | 7.2B | dense | 8K | 50.0 | |
| SciGLM | 6.2B | dense | 8K | 50.0 | |
| SeamlessM4T | 2.3B | dense | 4K | 50.0 | |
| SmolLM | 135M | dense | 2K | 50.0 | |
| SmolLM | 360M | dense | 2K | 50.0 | |
| SmolLM2 | 1.7B | dense | 8K | 50.0 | |
| Arctic | 395B (17B active) | moe | 4K | 50.0 | |
| Arctic | 480B (17B active) | moe | 4K | 50.0 | |
| SOLAR | 10.7B | dense | 4K | 50.0 | |
| Solar | 22B | dense | 4K | 50.0 | |
| Stable Diffusion | 3.5B | dense | 77 | 50.0 | |
| StableLM 2 | 12.1B | dense | 4K | 50.0 | |
| StableLM | 3B | dense | 4K | 50.0 | |
| StarCoder2 | 15.5B | dense | 16K | 42.0 | |
| StarCoder2 | 3.03B | dense | 16K | 29.0 | |
| StarCoder2 | 6.73B | dense | 16K | 35.0 | |
| TinyLlama | 1.1B | dense | 2K | 50.0 | |
| TinyLlama | 1.1B | dense | 2K | 50.0 | |
| Vicuna | 13B | dense | 4K | 50.0 | |
| Vicuna | 33B | dense | 2K | 50.0 | |
| Vicuna | 7B | dense | 4K | 50.0 | |
| VILA | 13B | dense | 4K | 62.0 | |
| VILA | 3B | dense | 4K | 44.0 | |
| VILA | 40B | dense | 8K | 73.0 | |
| Whisper | 74M | dense | 448 | 50.0 | |
| Whisper | 1.55B | dense | 448 | 50.0 | |
| Whisper | 769M | dense | 448 | 50.0 | |
| Whisper | 244M | dense | 448 | 50.0 | |
| WizardCoder | 33B | dense | 16K | 50.0 | |
| WizardMath | 70B | dense | 4K | 50.0 | |
| YaLM | 100B | dense | 2K | 50.0 | |
| Yi 1.5 | 34.4B | dense | 200K | 72.0 | |
| Yi 1.5 | 8.83B | dense | 4K | 62.0 | |
| Yi | 6B | dense | 200K | 50.0 | |
| Yi Coder | 8.8B | dense | 131K | 50.0 | |
| Yi | 102.6B (24B active) | moe | 33K | 74.0 | |
| Zephyr | 7B | dense | 33K | 50.0 |
Showing 253 of 253 models