Skip to content

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.

NameFamilyParamsArchitectureContextQuality
MiniLM23Mdense25650.0
Nova12Bdense300K50.0
Nova50Bdense300K50.0
Aya35Bdense131K50.0
Aya8Bdense8K50.0
Baichuan 213Bdense4K50.0
Baichuan 27Bdense4K50.0
BGE110Mdense51250.0
BGE335Mdense51250.0
BGE568Mdense8K50.0
BGE33Mdense51250.0
BioMistral7.2Bdense33K50.0
BTLM3Bdense8K50.0
Canary1Bdense4K50.0
Cerebras GPT13Bdense2K50.0
ChatGLM36Bdense131K50.0
ChatGLM9.4Bdense131K50.0
Claude175Bdense200K88.0
Claude70Bdense200K78.0
Claude20Bdense200K77.0
Claude200Bdense200K94.0
Claude70Bdense200K90.0
Code Llama13Bdense16K44.0
Code Llama34Bdense100K55.0
Code Llama70Bdense16K60.0
Code Llama7Bdense16K39.0
Gemma8.5Bdense8K52.0
CodeGen216Bdense2K50.0
Codestral22Bdense33K63.0
Codestral7.3Bhybrid262K50.0
CogVLM219Bdense8K50.0
Embed500Mdense51250.0
Command111Bdense256K81.0
Command R35Bdense131K68.0
Command R35Bdense128K50.0
Command R7Bdense131K50.0
Command R104Bdense131K78.0
DALL-E3.5Bdense4K50.0
DBRX132B (36B active)moe33K50.0
DBRX132B (36B active)moe33K50.0
DeepSeek Coder33Bdense16K50.0
DeepSeek Coder6.7Bdense16K50.0
DeepSeek Coder V2236B (21B active)moe131K50.0
DeepSeek LLM67Bdense4K66.0
DeepSeek Math7.24Bdense4K50.0
DeepSeek MoE16.4B (2.8B active)moe4K50.0
DeepSeek R1671B (37B active)moe131K92.0
DeepSeek R11.5Bdense131K42.0
DeepSeek R114.8Bdense131K50.0
DeepSeek R132.8Bdense131K50.0
DeepSeek R170.6Bdense131K50.0
DeepSeek R18Bdense131K50.0
DeepSeek V215.7B (2.4B active)moe33K50.0
DeepSeek V2236B (21B active)moe131K78.0
DeepSeek V3671B (37B active)moe131K86.0
Dolphin72Bdense33K50.0
E57.11Bdense33K50.0
ELYZA13Bdense4K50.0
Falcon11Bdense8K50.0
Falcon180Bdense2K60.0
Falcon40Bdense2K48.0
Falcon7Bdense2K37.0
Falcon Mamba7.27Bhybrid8K50.0
FinGPT7.2Bdense4K50.0
Florence770Mdense2K50.0
FLUX12Bdense51250.0
Gemini50B (12B active)moe1049K75.0
Gemini175B (40B active)moe2097K86.0
Gemini50B (15B active)moe1049K83.0
Gemini600B (150B active)moe2000K88.0
Gemma2.5Bdense8K50.0
Gemma 227Bdense8K73.0
Gemma 22.6Bdense8K44.0
Gemma 29.2Bdense8K68.0
Gemma 312Bdense131K71.0
Gemma 31Bdense33K35.0
Gemma 327Bdense131K76.0
Gemma 32Bdense8K42.0
Gemma 34.3Bdense131K54.0
GigaChat20Bdense8K50.0
GLM-49.4Bdense131K50.0
GPT-3.520Bdense16K67.0
GPT-4200B (50B active)moe128K86.0
GPT1500B (300B active)moe128K93.0
GPT-4200B (50B active)moe128K91.0
GPT-48Bdense128K80.0
Grok600B (120B active)moe131K90.0
Grok314B (50B active)moe131K87.0
GTE7.6Bdense33K50.0
H2O Danube500Mdense8K50.0
Llama 3.170.6Bdense131K82.0
Hermes 370.6Bdense131K50.0
Hermes 38.03Bdense131K50.0
Inflection100Bdense8K74.0
InfoXLM550Mdense51250.0
InternLM 2.519.9Bdense262K50.0
InternLM 2.57.74Bdense1049K50.0
InternLM20Bdense16K50.0
InternVL226Bdense33K50.0
JAIS30Bdense8K50.0
Jamba398Bhybrid256K50.0
Jamba52Bhybrid256K50.0
Jamba52B (12B active)moe256K66.0
StableLM70Bdense8K50.0
Jina Embeddings570Mdense8K50.0
Kimi1000B (32B active)moe131K50.0
KULLM12.8Bdense4K50.0
Llama 213Bdense4K47.0
Llama 270Bdense4K62.0
Llama 27Bdense4K40.0
Llama 370.6Bdense8K80.0
Llama 370.6Bdense1049K50.0
Llama 38Bdense8K63.0
Llama 3.1405Bdense131K88.0
Llama 3.170.6Bdense131K82.0
Llama 3.170.6Bdense131K50.0
Llama 3.18.03Bdense131K65.0
Llama 3.151Bdense131K78.0
Llama 3.170.6Bdense131K83.0
Llama 3.170.6Bdense131K80.0
Llama 3.211Bdense131K50.0
Llama 3.21.24Bdense131K38.0
Llama 3.23.21Bdense131K55.0
Llama 3.290Bdense131K50.0
Llama 3.288.8Bdense131K84.0
Llama 3.370.6Bdense131K84.0
Llama 3.38Bdense131K50.0
Llama 42000B (400B active)moe1049K93.0
Llama 4400B (17B active)moe1049K89.0
Llama 4109B (17B active)moe10486K76.0
Llama Guard1Bdense131K50.0
Llama Guard8Bdense131K50.0
Marco7.6Bdense66K50.0
Meditron70Bdense4K50.0
Megatron-Turing530Bdense2K58.0
Ministral8Bdense131K50.0
Nemotron4Bdense8K50.0
Nemotron8Bdense8K62.0
Mistral7.3Bdense33K56.0
Mistral Large123Bdense131K82.0
Mistral Large123Bdense131K50.0
Mistral70Bdense131K80.0
Mistral Nemo12Bdense131K62.0
Mistral Small24Bdense33K68.0
Mistral Small24Bdense131K50.0
Mixtral141B (39B active)moe66K73.0
Mixtral46.7B (12.9B active)moe33K67.0
Mixtral46.7B (12.9B active)moe33K69.0
MPT30Bdense8K48.0
MPT6.7Bdense66K36.0
E5560Mdense51250.0
Nekomata14Bdense4K50.0
Nemotron15Bdense4K72.0
Nemotron340Bdense131K85.0
Nemotron70.6Bdense131K83.0
Nemotron4Bdense8K48.0
Nomic Embed137Mdense8K50.0
NV Embed7.85Bdense33K50.0
NV EmbedQA330Mdense51250.0
NV EmbedQA7.24Bdense33K50.0
NV Retriever330Mdense51250.0
o1200B (50B active)moe200K95.0
o170Bdense128K86.0
o370Bdense200K89.0
OctoCoder15.5Bdense8K50.0
OLMo 213Bdense4K50.0
OLMo 27Bdense4K50.0
OpenELM3Bdense2K50.0
OpenHermes7Bdense33K50.0
Orca13Bdense4K50.0
PaLI-Gemma2.9Bdense8K50.0
Parakeet600Mdense4K50.0
Parakeet1.1Bdense4K50.0
Phi1.3Bdense2K38.0
Phi1.3Bdense2K50.0
Phi2.7Bdense2K50.0
Phi 314Bdense131K76.0
Phi 33.8Bdense131K64.0
Phi 37Bdense131K72.0
Phi41.9B (6.6B active)moe131K74.0
Phi 3.54.2Bdense131K50.0
Phi3.8Bdense131K70.0
Phi14.7Bdense16K83.0
Pixtral12Bdense131K50.0
Prometheus7.24Bdense8K50.0
Qwen 1.514.3B (2.7B active)moe33K50.0
Qwen 27.6Bdense33K50.0
Qwen 2 VL2.2Bdense33K50.0
Qwen 2.5500Mdense33K50.0
Qwen 2.51.5Bdense33K50.0
Qwen 2.514.8Bdense131K76.0
Qwen 2.532.5Bdense131K81.0
Qwen 2.53.09Bdense33K58.0
Qwen 2.572.7Bdense131K84.0
Qwen 2.57.6Bdense131K70.0
Qwen 2.5 Coder1.5Bdense33K40.0
Qwen 2.5 Coder14.7Bdense131K50.0
Qwen 2.532.5Bdense131K50.0
Qwen 2.5 Coder3.1Bdense33K50.0
Qwen 2.5 Coder7.6Bdense131K50.0
Qwen 2.5 Math72.7Bdense4K50.0
Qwen 2.5 Math7.6Bdense4K50.0
Qwen 2.5 VL72.7Bdense131K50.0
Qwen 2.5 VL7.6Bdense131K50.0
Qwen 3600Mdense131K50.0
Qwen 31.7Bdense131K50.0
Qwen 3235B (22B active)moe131K88.0
Qwen 330.5B (3.3B active)moe131K70.0
Qwen 332.8Bdense131K80.0
Qwen 34Bdense131K57.0
Qwen 38.2Bdense131K67.0
RecurrentGemma2.7Bdense8K50.0
Reka70Bdense128K76.0
Replit Code3.3Bdense4K50.0
RWKV14.1Bhybrid33K50.0
SantaCoder1.1Bdense2K50.0
SaulLM7.2Bdense8K50.0
SciGLM6.2Bdense8K50.0
SeamlessM4T2.3Bdense4K50.0
SmolLM135Mdense2K50.0
SmolLM360Mdense2K50.0
SmolLM21.7Bdense8K50.0
Arctic395B (17B active)moe4K50.0
Arctic480B (17B active)moe4K50.0
SOLAR10.7Bdense4K50.0
Solar22Bdense4K50.0
Stable Diffusion3.5Bdense7750.0
StableLM 212.1Bdense4K50.0
StableLM3Bdense4K50.0
StarCoder215.5Bdense16K42.0
StarCoder23.03Bdense16K29.0
StarCoder26.73Bdense16K35.0
TinyLlama1.1Bdense2K50.0
TinyLlama1.1Bdense2K50.0
Vicuna13Bdense4K50.0
Vicuna33Bdense2K50.0
Vicuna7Bdense4K50.0
VILA13Bdense4K62.0
VILA3Bdense4K44.0
VILA40Bdense8K73.0
Whisper74Mdense44850.0
Whisper1.55Bdense44850.0
Whisper769Mdense44850.0
Whisper244Mdense44850.0
WizardCoder33Bdense16K50.0
WizardMath70Bdense4K50.0
YaLM100Bdense2K50.0
Yi 1.534.4Bdense200K72.0
Yi 1.58.83Bdense4K62.0
Yi6Bdense200K50.0
Yi Coder8.8Bdense131K50.0
Yi102.6B (24B active)moe33K74.0
Zephyr7Bdense33K50.0

Showing 253 of 253 models