Every AI model in the arena's universe
539 models from the labs and platforms that build and serve them. What each one is for, who made it, and whether you can download it and run it yourself.
Directory snapshot: August 2026
Weights you can download and run yourself.
Showing 233 of 539 models
- Apertus 70B InstructSwiss AI Initiative (ETH/EPFL)70B parametersOpen weights
- Apertus 8B InstructSwiss AI Initiative (ETH/EPFL)8B parametersOpen weights
- Arctic InstructSnowflakeOpen weights
- DBRX InstructDatabricksOpen weights
- DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)Nous Research8B parametersOpen weights
- DeepHermes 3 - Mistral 24B Preview (Non-reasoning)Nous Research24B parametersOpen weights
- DeepSeek Coder V2 Lite InstructDeepSeekOpen weights
- DeepSeek LLM 67B Chat (V1)DeepSeek67B parametersOpen weights
- DeepSeek V3 (Dec '24)DeepSeekOpen weights
- DeepSeek V3 0324DeepSeekOpen weights
- DeepSeek V3.1 (Non-reasoning)DeepSeekOpen weights
- DeepSeek V3.1 (Reasoning)DeepSeekOpen weights
- DeepSeek V3.1 Terminus (Non-reasoning)DeepSeekOpen weights
- DeepSeek V3.1 Terminus (Reasoning)DeepSeekOpen weights
- DeepSeek V3.2 (Non-reasoning)DeepSeekOpen weights
- DeepSeek V3.2 (Reasoning)DeepSeekOpen weights
- DeepSeek V3.2 Exp (Non-reasoning)DeepSeekOpen weights
- DeepSeek V3.2 Exp (Reasoning)DeepSeekOpen weights
- DeepSeek V3.2 SpecialeDeepSeekOpen weights
- DeepSeek-Coder-V2DeepSeekOpen weights
- DeepSeek-V2-ChatDeepSeekOpen weights
- DeepSeek-V2.5DeepSeekOpen weights
- DeepSeek-V2.5 (Dec '24)DeepSeekOpen weights
- Exaone 4.0 1.2B (Non-reasoning)LG AI Research1.2B parametersOpen weights
- Exaone 4.0 1.2B (Reasoning)LG AI Research1.2B parametersOpen weights
- EXAONE 4.0 32B (Non-reasoning)LG AI Research32B parametersOpen weights
- EXAONE 4.0 32B (Reasoning)LG AI Research32B parametersOpen weights
- EXAONE 4.5 33BLG AI Research33B parametersOpen weights
- EXAONE 4.5 33B (Non-reasoning)LG AI Research33B parametersOpen weights
- Falcon-H1R-7BTII7B parametersOpen weights
- G9v3-39A5BAI9StarsOpen weights
- G9v3-3BAI9Stars3B parametersOpen weights
- Gemma 3 12B InstructGoogle12B parametersOpen weights
- Gemma 3 1B InstructGoogle1B parametersOpen weights
- Gemma 3 270MGoogle0.3B parametersOpen weights
- Gemma 3 27B InstructGoogle27B parametersOpen weights
- Gemma 3 4B InstructGoogle4B parametersOpen weights
- Gemma 3n E2B InstructGoogleOpen weights
- Gemma 3n E4B InstructGoogleOpen weights
- Gemma 3n E4B Instruct Preview (May '25)GoogleOpen weights
- Gemma 4 12B (Non-reasoning)Google12B parametersOpen weights
- Gemma 4 12B (Reasoning)Google12B parametersOpen weights
- Gemma 4 26B A4B (Non-reasoning)Google26B total / 4B active (MoE)Open weights
- Gemma 4 26B A4B (Reasoning)Google26B total / 4B active (MoE)Open weights
- Gemma 4 31B (Non-reasoning)Google31B parametersOpen weights
- Gemma 4 31B (Reasoning)Google31B parametersOpen weights
- Gemma 4 E2B (Non-reasoning)GoogleOpen weights
- Gemma 4 E2B (Reasoning)GoogleOpen weights
- Gemma 4 E4B (Non-reasoning)GoogleOpen weights
- Gemma 4 E4B (Reasoning)GoogleOpen weights
- gpt-oss-120bOpenAI120B parametersOpen weights
- gpt-oss-20bOpenAI20B parametersOpen weights
- Granite 3.3 8B (Non-reasoning)IBM8B parametersOpen weights
- Granite 4.0 1BIBM1B parametersOpen weights
- Granite 4.0 350MIBM0.3B parametersOpen weights
- Granite 4.0 H 1BIBM1B parametersOpen weights
- Granite 4.0 H 350MIBM0.3B parametersOpen weights
- Granite 4.0 H SmallIBMOpen weights
- Granite 4.0 MicroIBMOpen weights
- Granite 4.1 30BIBM30B parametersOpen weights
- Granite 4.1 3BIBM3B parametersOpen weights
- Granite 4.1 8BIBM8B parametersOpen weights
- Hermes 3 - Llama-3.1 70BNous Research70B parametersOpen weights
- Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research405B parametersOpen weights
- Hermes 4 - Llama-3.1 405B (Reasoning)Nous Research405B parametersOpen weights
- Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research70B parametersOpen weights
- Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research70B parametersOpen weights
- HyperCLOVA X SEED Think (32B)NaverOpen weights
- K-EXAONE (Non-reasoning)LG AI ResearchOpen weights
- K-EXAONE (Reasoning)LG AI ResearchOpen weights
- Ling 2.6 FlashInclusionAI (Ant Group)Open weights
- Ling-1TInclusionAI (Ant Group)Open weights
- Ling-2.6-1TInclusionAI (Ant Group)Open weights
- Ling-flash-2.0InclusionAI (Ant Group)Open weights
- Ling-mini-2.0InclusionAI (Ant Group)Open weights
- Llama 2 Chat 13BMeta13B parametersOpen weights
- Llama 2 Chat 70BMeta70B parametersOpen weights
- Llama 2 Chat 7BMeta7B parametersOpen weights
- Llama 3 Instruct 70BMeta70B parametersOpen weights
- Llama 3 Instruct 8BMeta8B parametersOpen weights
- Llama 3.1 Instruct 405BMeta405B parametersOpen weights
- Llama 3.1 Instruct 70BMeta70B parametersOpen weights
- Llama 3.1 Instruct 8BMeta8B parametersOpen weights
- Llama 3.1 Nemotron Instruct 70BNVIDIA70B parametersOpen weights
- Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)NVIDIA4B parametersOpen weights
- Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA253B parametersOpen weights
- Llama 3.2 Instruct 11B (Vision)Meta11B parametersOpen weights
- Llama 3.2 Instruct 1BMeta1B parametersOpen weights
- Llama 3.2 Instruct 3BMeta3B parametersOpen weights
- Llama 3.2 Instruct 90B (Vision)Meta90B parametersOpen weights
- Llama 3.3 Instruct 70BMeta70B parametersOpen weights
- Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)NVIDIA49B parametersOpen weights
- Llama 3.3 Nemotron Super 49B v1 (Reasoning)NVIDIA49B parametersOpen weights
- Llama 4 MaverickMetaOpen weights
- Llama 4 ScoutMetaOpen weights
- Llama 65BMeta65B parametersOpen weights
- Llama Nemotron Super 49B v1.5 (Non-reasoning)NVIDIA49B parametersOpen weights
- Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIA49B parametersOpen weights
- LongCat 2.0MeituanOpen weights
- LongCat Flash LiteMeituanOpen weights
- Mi:dm K 2.5 ProKT CorporationOpen weights
- Mi:dm K 2.5 Pro PreviewKT CorporationOpen weights
- Mistral 7B InstructMistral7B parametersOpen weights
- Mistral Large (Feb '24)MistralOpen weights
- Mistral Large 2 (Jul '24)MistralOpen weights
- Mistral Large 2 (Nov '24)MistralOpen weights
- Mistral Large 3MistralOpen weights
- Mistral MediumMistralOpen weights
- Mistral Medium 3MistralOpen weights
- Mistral Medium 3.1MistralOpen weights
- Mistral Medium 3.5MistralOpen weights
- Mistral SabaMistralOpen weights
- Mistral Small (Feb '24)MistralOpen weights
- Mistral Small (Sep '24)MistralOpen weights
- Mistral Small 3MistralOpen weights
- Mistral Small 3.1MistralOpen weights
- Mistral Small 3.2MistralOpen weights
- Mistral Small 4 (Non-reasoning)MistralOpen weights
- Mistral Small 4 (Reasoning)MistralOpen weights
- Mixtral 8x22B InstructMistral176B total / 44B active (MoE)Open weights
- Mixtral 8x7B InstructMistral56B total / 14B active (MoE)Open weights
- Motif 3 (Beta)Motif TechnologiesOpen weights
- Motif-2-12.7B-ReasoningMotif Technologies12.7B parametersOpen weights
- Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA30B total / 3B active (MoE)Open weights
- Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA550B total / 55B active (MoE)Open weights
- Nemotron Cascade 2 30B A3BNVIDIA30B total / 3B active (MoE)Open weights
- Nex-N2-ProNex AGIOpen weights
- NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA30B total / 3B active (MoE)Open weights
- NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA30B total / 3B active (MoE)Open weights
- NVIDIA Nemotron 3 Nano 4BNVIDIA4B parametersOpen weights
- NVIDIA Nemotron 3 Super 120B A12B (Reasoning)NVIDIA120B total / 12B active (MoE)Open weights
- NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)NVIDIA12B parametersOpen weights
- NVIDIA Nemotron Nano 12B v2 VL (Reasoning)NVIDIA12B parametersOpen weights
- NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA9B parametersOpen weights
- NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA9B parametersOpen weights
- Pixtral LargeMistralOpen weights
- Qwen Chat 14BAlibaba Cloud14B parametersOpen weights
- Qwen Chat 72BAlibaba Cloud72B parametersOpen weights
- Qwen1.5 Chat 110BAlibaba Cloud110B parametersOpen weights
- Qwen2 Instruct 72BAlibaba Cloud72B parametersOpen weights
- Qwen2.5 Coder Instruct 32BAlibaba Cloud32B parametersOpen weights
- Qwen2.5 Coder Instruct 7BAlibaba Cloud7B parametersOpen weights
- Qwen2.5 Instruct 32BAlibaba Cloud32B parametersOpen weights
- Qwen2.5 Instruct 72BAlibaba Cloud72B parametersOpen weights
- Qwen2.5 MaxAlibaba CloudOpen weights
- Qwen2.5 TurboAlibaba CloudOpen weights
- Qwen3 0.6B (Non-reasoning)Alibaba Cloud0.6B parametersOpen weights
- Qwen3 0.6B (Reasoning)Alibaba Cloud0.6B parametersOpen weights
- Qwen3 1.7B (Non-reasoning)Alibaba Cloud1.7B parametersOpen weights
- Qwen3 1.7B (Reasoning)Alibaba Cloud1.7B parametersOpen weights
- Qwen3 14B (Non-reasoning)Alibaba Cloud14B parametersOpen weights
- Qwen3 14B (Reasoning)Alibaba Cloud14B parametersOpen weights
- Qwen3 235B A22B (Non-reasoning)Alibaba Cloud235B total / 22B active (MoE)Open weights
- Qwen3 235B A22B (Reasoning)Alibaba Cloud235B total / 22B active (MoE)Open weights
- Qwen3 235B A22B 2507 (Reasoning)Alibaba Cloud235B total / 22B active (MoE)Open weights
- Qwen3 235B A22B 2507 InstructAlibaba Cloud235B total / 22B active (MoE)Open weights
- Qwen3 30B A3B (Non-reasoning)Alibaba Cloud30B total / 3B active (MoE)Open weights
- Qwen3 30B A3B (Reasoning)Alibaba Cloud30B total / 3B active (MoE)Open weights
- Qwen3 30B A3B 2507 (Reasoning)Alibaba Cloud30B total / 3B active (MoE)Open weights
- Qwen3 30B A3B 2507 InstructAlibaba Cloud30B total / 3B active (MoE)Open weights
- Qwen3 32B (Non-reasoning)Alibaba Cloud32B parametersOpen weights
- Qwen3 32B (Reasoning)Alibaba Cloud32B parametersOpen weights
- Qwen3 4B (Non-reasoning)Alibaba Cloud4B parametersOpen weights
- Qwen3 4B (Reasoning)Alibaba Cloud4B parametersOpen weights
- Qwen3 4B 2507 (Reasoning)Alibaba Cloud4B parametersOpen weights
- Qwen3 4B 2507 InstructAlibaba Cloud4B parametersOpen weights
- Qwen3 8B (Non-reasoning)Alibaba Cloud8B parametersOpen weights
- Qwen3 8B (Reasoning)Alibaba Cloud8B parametersOpen weights
- Qwen3 Coder 30B A3B InstructAlibaba Cloud30B total / 3B active (MoE)Open weights
- Qwen3 Coder 480B A35B InstructAlibaba Cloud480B total / 35B active (MoE)Open weights
- Qwen3 Coder NextAlibaba CloudOpen weights
- Qwen3 MaxAlibaba CloudOpen weights
- Qwen3 Max (Preview)Alibaba CloudOpen weights
- Qwen3 Max ThinkingAlibaba CloudOpen weights
- Qwen3 Max Thinking (Preview)Alibaba CloudOpen weights
- Qwen3 Next 80B A3B (Reasoning)Alibaba Cloud80B total / 3B active (MoE)Open weights
- Qwen3 Next 80B A3B InstructAlibaba Cloud80B total / 3B active (MoE)Open weights
- Qwen3 Omni 30B A3B (Reasoning)Alibaba Cloud30B total / 3B active (MoE)Open weights
- Qwen3 Omni 30B A3B InstructAlibaba Cloud30B total / 3B active (MoE)Open weights
- Qwen3 VL 235B A22B (Reasoning)Alibaba Cloud235B total / 22B active (MoE)Open weights
- Qwen3 VL 235B A22B InstructAlibaba Cloud235B total / 22B active (MoE)Open weights
- Qwen3 VL 30B A3B (Reasoning)Alibaba Cloud30B total / 3B active (MoE)Open weights
- Qwen3 VL 30B A3B InstructAlibaba Cloud30B total / 3B active (MoE)Open weights
- Qwen3 VL 32B (Reasoning)Alibaba Cloud32B parametersOpen weights
- Qwen3 VL 32B InstructAlibaba Cloud32B parametersOpen weights
- Qwen3 VL 4B (Reasoning)Alibaba Cloud4B parametersOpen weights
- Qwen3 VL 4B InstructAlibaba Cloud4B parametersOpen weights
- Qwen3 VL 8B (Reasoning)Alibaba Cloud8B parametersOpen weights
- Qwen3 VL 8B InstructAlibaba Cloud8B parametersOpen weights
- Qwen3.5 0.8B (Non-reasoning)Alibaba Cloud0.8B parametersOpen weights
- Qwen3.5 0.8B (Reasoning)Alibaba Cloud0.8B parametersOpen weights
- Qwen3.5 122B A10B (Non-reasoning)Alibaba Cloud122B total / 10B active (MoE)Open weights
- Qwen3.5 122B A10B (Reasoning)Alibaba Cloud122B total / 10B active (MoE)Open weights
- Qwen3.5 27B (Non-reasoning)Alibaba Cloud27B parametersOpen weights
- Qwen3.5 27B (Reasoning)Alibaba Cloud27B parametersOpen weights
- Qwen3.5 2B (Non-reasoning)Alibaba Cloud2B parametersOpen weights
- Qwen3.5 2B (Reasoning)Alibaba Cloud2B parametersOpen weights
- Qwen3.5 35B A3B (Non-reasoning)Alibaba Cloud35B total / 3B active (MoE)Open weights
- Qwen3.5 35B A3B (Reasoning)Alibaba Cloud35B total / 3B active (MoE)Open weights
- Qwen3.5 397B A17B (Non-reasoning)Alibaba Cloud397B total / 17B active (MoE)Open weights
- Qwen3.5 397B A17B (Reasoning)Alibaba Cloud397B total / 17B active (MoE)Open weights
- Qwen3.5 4B (Non-reasoning)Alibaba Cloud4B parametersOpen weights
- Qwen3.5 4B (Reasoning)Alibaba Cloud4B parametersOpen weights
- Qwen3.5 9B (Non-reasoning)Alibaba Cloud9B parametersOpen weights
- Qwen3.5 9B (Reasoning)Alibaba Cloud9B parametersOpen weights
- Qwen3.5 Omni FlashAlibaba CloudOpen weights
- Qwen3.5 Omni PlusAlibaba CloudOpen weights
- Qwen3.6 27B (Non-reasoning)Alibaba Cloud27B parametersOpen weights
- Qwen3.6 27B (Reasoning)Alibaba Cloud27B parametersOpen weights
- Qwen3.6 35B A3B (Non-reasoning)Alibaba Cloud35B total / 3B active (MoE)Open weights
- Qwen3.6 35B A3B (Reasoning)Alibaba Cloud35B total / 3B active (MoE)Open weights
- Qwen3.6 Max PreviewAlibaba CloudOpen weights
- Qwen3.6 PlusAlibaba CloudOpen weights
- Qwen3.7 MaxAlibaba CloudOpen weights
- Qwen3.7 PlusAlibaba CloudOpen weights
- QwQ 32BAlibaba Cloud32B parametersOpen weights
- QwQ 32B-PreviewAlibaba Cloud32B parametersOpen weights
- Ring-1TInclusionAI (Ant Group)Open weights
- Ring-2.6-1TInclusionAI (Ant Group)Open weights
- Ring-flash-2.0InclusionAI (Ant Group)Open weights
- Sarvam 105BSarvam105B parametersOpen weights
- Sarvam 30BSarvam30B parametersOpen weights
- Sarvam M (Reasoning)SarvamOpen weights
- Solar MiniUpstageOpen weights
- Solar Open 100B (Reasoning)Upstage100B parametersOpen weights
- Solar Pro 2 (Non-reasoning)UpstageOpen weights
- Solar Pro 2 (Preview) (Non-reasoning)UpstageOpen weights
- Solar Pro 2 (Preview) (Reasoning)UpstageOpen weights
- Solar Pro 2 (Reasoning)UpstageOpen weights
- Solar Pro 3UpstageOpen weights
- Tri-21B-ThinkTrillion Labs21B parametersOpen weights
- Tri-21B-think PreviewTrillion Labs21B parametersOpen weights
- Trinity Large ThinkingArcee AIOpen weights
Browsing by generation instead? Every model page links to its family, so you can see the whole line-up side by side. Ratings live on the leaderboard — only models currently in the arena pool are ranked there.