Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Sign in Sign up
Beta
Model Directory

Model directory

All models as a filterable list – by maker, architecture or name.

110 Modelle
ModellHerstellerArchitekturParameterBenchmarksPerformanceHarness
Codestral-22B-v0.122B Mistral AI Dense 22B 98 98 0
Command-A-Plus-218B-A25B218B Cohere - 218B 0 0 0
command-a-reasoning-08-2025111B Cohere - 111B 42 42 0
DeepSeek-V4-Flash290.9B DeepSeek MoE 290.9B 15 15 0
DeepSeek-V4-Flash-284B-A13B284B DeepSeek MoE 284B 23 23 0
Devstral-2-123B-Instruct-2512123B Mistral AI Dense 123B 53 53 0
Devstral-Small-2-24B-Instruct-251224B Mistral AI Dense 24B 107 103 4
Devstral-Small-250724B Mistral AI Dense 24B 95 95 0
gemma-2-27b-it27B Google Dense 27B 3 3 0
gemma-2-2b-it2B Google Dense 2B 9 9 0
gemma-2-9b-it9B Google Dense 9B 3 3 0
gemma-3n-E4B-it8B Google Dense 8B 9 9 0
gemma-4-12B-it12B Google Dense 12B 100 100 0
gemma-4-12B-it-assistant12B Google Dense 12B 0 0 0
Gemma-4-26B-A4B26B Google MoE 26B 7 7 0
Gemma-4-26B-A4B-it26B Google MoE 26B 90 83 7
gemma-4-26B-A4B-it-assistant26B Google MoE 26B 3 3 0
gemma-4-31B-it31B Google Dense 31B 55 54 1
gemma-4-31B-it-assistant31B Google Dense 31B 0 0 0
gemma-4-E2B-it5B Google Dense 5B 97 97 0
gemma-4-E2B-it-assistant5B Google Dense 5B 0 0 0
gemma-4-E4B-it8B Google Dense 8B 53 53 0
gemma-4-E4B-it-assistant8B Google Dense 8B 0 0 0
GLM-4.5-Air106B Z.ai (Zhipu) MoE 106B 60 60 0
glm-4.7-flash Z.ai (Zhipu) - - 10 10 0
glm-5.2-colibri744B Z.ai (Zhipu) MoE 744B 9 9 0
gpt-oss-120b120B OpenAI MoE 120B 54 54 0
gpt-oss-20b20B OpenAI MoE 20B 155 155 0
Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated30B Qwen (Alibaba) MoE 30B 6 6 0
Jev-1.13.0 TypeSafe AI - - 2 0 2
Kolibri-178.1B Aleph Alpha MoE 78.1B 22 15 7
Laguna-M.1 Poolside - - 77 77 0
Laguna-S-2.1-INT4 Poolside - - 65 65 0
Laguna-XS-2.1 Poolside - - 127 127 0
Laya Convai Innovations - - 1 0 1
Ling-3.0-flash127.5B inclusionAI MoE 127.5B 87 87 0
Llama-3.1-Nemotron-Nano-4B-v1.14.5B NVIDIA Dense 4.5B 6 6 0
Llama-3.1-Nemotron-Ultra-253B-v1253B NVIDIA Dense 253B 53 53 0
Llama-3.2-1B-Instruct1B Meta Dense 1B 14 14 0
Llama-3.2-3B-Instruct3B Meta Dense 3B 21 21 0
Llama-3.3-Nemotron-Super-49B-v1.549B NVIDIA Dense 49B 49 49 0
Magistral-Small-250924B Mistral AI Dense 24B 101 101 0
Mamba-Codestral-7B-v0.17B Mistral AI Dense 7B 0 0 0
Meta-Llama-3.1-8B-Instruct8B Meta Dense 8B 117 117 0
minimax-m2-awq230B MiniMax MoE 230B 9 9 0
MiniMax-M2.5230B MiniMax MoE 230B 98 86 12
MiniMax-M2.7230B MiniMax MoE 230B 51 49 2
Ministral-3-14B-Reasoning-251214B Mistral AI Dense 14B 123 123 0
Mistral-Medium-3.5-128B128B Mistral AI Dense 128B 31 31 0
Mistral-Small-24B-Instruct-2501 Mistral AI Dense - 3 3 0
Mistral-Small-3.1-24B-Instruct-250324B Mistral AI Dense 24B 78 78 0
Mistral-Small-4-119B-2603119B Mistral AI Dense 119B 26 26 0
Muse-Glimmer-30B30B Meta Dense Causal Transformer + Perception Encoder (multimodal, 131k Kontext) 30B 15 15 0
Nemotron-3-Nano-30B-A3B30B NVIDIA MoE 30B 92 92 0
Nemotron-3-Nano-4B4B NVIDIA Dense 4B 67 67 0
Nemotron-3-Nano-Omni-30B-A3B-Reasoning30B NVIDIA MoE 30B 62 62 0
Nemotron-3-Super-120B-A12B120B NVIDIA MoE 120B 59 59 0
Nemotron-3-Super-120B-A12B-Q8120B NVIDIA MoE 120B 0 0 0
Nemotron-3.5-Lightning-30B-A3B30B NVIDIA Hybrid Mamba-2 + MoE (3B aktiv) 30B 33 33 0
Nemotron-Cascade-2-30B-A3B30B NVIDIA MoE 30B 79 77 2
Nemotron-H-47B-Reasoning-128K47B NVIDIA Dense 47B 63 63 0
Nemotron-Labs-3-Puzzle-75B-A9B75B NVIDIA MoE 75B 0 0 0
North-Mini-Code-1.0 Cohere - - 83 83 0
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B120B NVIDIA MoE 120B 6 6 0
Open-Jev-27B-v1.127.00B Zefan Cai / Open-Jev Dense 27.00B 1 0 1
OpenReasoning-Nemotron-32B32B NVIDIA Dense 32B 53 53 0
Ornith-1.0-35B35B DeepReinforce Dense 35B 39 39 0
Ornith-1.0-35B-FP835B DeepReinforce Dense 35B 0 0 0
Ornith-1.0-9B9B DeepReinforce Dense 9B 109 109 0
Ornith-1.5-35B-A3B35B DeepReinforce MoE 35B 21 21 0
Ornith-1.5-35B-A3B-FP835B DeepReinforce MoE 35B 0 0 0
Ornith-1.5-397B397B DeepReinforce MoE 397B 0 0 0
Ornith-1.5-9B9B DeepReinforce Dense 9B 15 15 0
Phi-3.5-mini-instruct3.8B microsoft Dense 3.8B 6 6 0
Qwen-AgentWorld-35B-A3B35B Qwen (Alibaba) MoE 35B 78 78 0
Qwen2.5-0.5B-Instruct Qwen (Alibaba) Dense - 3 3 0
Qwen2.5-1.5B-Instruct Qwen (Alibaba) Dense - 3 3 0
Qwen2.5-32B-Instruct-AWQ32B Qwen (Alibaba) Dense 32B 63 61 2
Qwen2.5-3B-Instruct3B Qwen (Alibaba) Dense 3B 21 21 0
Qwen2.5-72B-Instruct72B Qwen (Alibaba) Dense 72B 32 32 0
Qwen2.5-7B-Instruct7B Qwen (Alibaba) Dense 7B 12 12 0
Qwen2.5-Coder-32B-Instruct32B Qwen (Alibaba) Dense 32B 104 104 0
Qwen2.5-Coder-7B-Instruct Qwen (Alibaba) Dense - 3 3 0
Qwen3-0.6B0.6B Qwen (Alibaba) Dense 0.6B 20 20 0
Qwen3-1.7B1.7B Qwen (Alibaba) Dense 1.7B 17 17 0
Qwen3-14B14B Qwen (Alibaba) Dense 14B 10 10 0
Qwen3-30B-A3B30B Qwen (Alibaba) MoE 30B 3 3 0
Qwen3-30B-A3B-Instruct-250730B Qwen (Alibaba) MoE 30B 131 131 0
Qwen3-30B-A3B-Thinking-250730B Qwen (Alibaba) MoE 30B 115 115 0
Qwen3-32B32B Qwen (Alibaba) Dense 32B 3 3 0
Qwen3-4B4B Qwen (Alibaba) Dense 4B 17 17 0
Qwen3-8B8.2B Qwen (Alibaba) Dense 8.2B 12 12 0
Qwen3-Coder-30B-A3B-Instruct30B Qwen (Alibaba) MoE 30B 129 129 0
Qwen3-Coder-Next Qwen (Alibaba) MoE - 57 57 0
Qwen3-Omni-30B-A3B-Thinking30B Qwen (Alibaba) MoE 30B 74 74 0
Qwen3-VL-30B-A3B-Instruct30B Qwen (Alibaba) MoE 30B 105 105 0
Qwen3.5-122B-A10B122B Qwen (Alibaba) MoE 122B 58 58 0
Qwen3.5-122B-A10B-Q8122B Qwen (Alibaba) MoE 122B 0 0 0
Qwen3.5-35B-A3B35B Qwen (Alibaba) MoE 35B 111 111 0
Qwen3.6-27B27B Qwen (Alibaba) Dense 27B 75 73 2
Qwen3.6-35B-A3B35B Qwen (Alibaba) MoE 35B 166 166 0
Qwen3.6-35B-A3B-AWQ35.00B Qwen (Alibaba) MoE 35.00B 4 0 4
Qwen3.8-27B27B Qwen (Alibaba) Qwen3_5ForConditionalGeneration (multimodal, image-text-to-text) 27B 57 57 0
Qwen3.8-27B-Uncensored27.00B Qwen (Alibaba) Dense 27.00B 3 0 3
Qwen3.8-Flash-Next180B Qwen (Alibaba) MoE 180B 56 56 0
Qwen3.8-Flash-Next-Uncensored-NVFP4180B Qwen (Alibaba) MoE 180B 1 0 1
Seed-OSS-36B-Instruct36B ByteDance Seed - 36B 85 85 0
SmolLM2-1.7B-Instruct1.7B HuggingFaceTB Dense 1.7B 5 5 0
Step-3.5-Flash StepFun - - 3 3 0
Tencent-Hy3-295B-A21B295B Tencent MoE 295B 0 0 0