Powered bymario-alka.degodcore.detricoma.de
Model Directory

Modellverzeichnis

Alle Modelle als filterbare Liste - nach Hersteller, Architektur oder Name.

60 Modelle
ModellHerstellerArchitekturParameterBenchmarksPerformanceHarness
Codestral-22B-v0.1 Mistral AI Dense 22B 4 4 0
Command-A-Plus-218B-A25B Cohere - - 0 0 0
command-a-reasoning-08-2025 Cohere - - 0 0 0
DeepSeek-V4-Flash-284B-A13B DeepSeek MoE - 0 0 0
Devstral-2-123B-Instruct-2512 Mistral AI Dense 123B 1 1 0
Devstral-Small-2-24B-Instruct-2512 Mistral AI Dense 24B 8 4 4
Devstral-Small-2507 Mistral AI Dense 24B 6 6 0
Gemma-4-26B-A4B-it Google MoE 26B 8 1 7
gemma-4-31b-it-int8 Google Dense 31B 4 4 0
gemma4:31b Google Dense 31B 1 0 1
GLM-4.5-Air Z.ai (Zhipu) MoE 106B 2 2 0
gpt-oss-120b OpenAI MoE 117B 2 2 0
gpt-oss-20b OpenAI MoE 21B 6 6 0
Laguna-M.1 Poolside - - 0 0 0
Laguna-M.1-FP8 Poolside - - 0 0 0
Laguna-M.1-GGUF-Q4_K_M Poolside - - 0 0 0
Laguna-M.1-NVFP4 Poolside - - 0 0 0
Laguna-S-2.1-INT4 Poolside - - 1 1 0
Laguna-XS-2.1 Poolside - - 0 0 0
Laguna-XS-2.1-GGUF-Q4_K_M Poolside - - 0 0 0
Laguna-XS-2.1-INT4 Poolside - - 1 1 0
Llama-3_1-Nemotron-Ultra-253B-v1 NVIDIA Dense 253B 0 0 0
Llama-3_3-Nemotron-Super-49B-v1_5 NVIDIA Dense 49B 0 0 0
Magistral-Small-2509 Mistral AI Dense 24B 6 6 0
Mamba-Codestral-7B-v0.1 Mistral AI Dense 7B 0 0 0
Minimax-2.5 MiniMax MoE 230B 1 1 0
MiniMax-M2.5 MiniMax MoE 230B 10 1 9
MiniMax-M2.5-BF16-INT4-AWQ MiniMax MoE 230B 3 0 3
MiniMax-M2.7 MiniMax MoE 230B 1 1 0
MiniMax-M2.7-AWQ-4bit MiniMax MoE 230B 3 1 2
Ministral-3-14B-Reasoning-2512 Mistral AI Dense 14B 3 3 0
Mistral-Medium-3.5-128B Mistral AI Dense 128B 1 1 0
Mistral-Small-3.1-24B-Instruct-2503 Mistral AI Dense 24B 9 9 0
Mistral-Small-4-119B-2603 Mistral AI Dense 119B 1 1 0
Nemotron-3-Nano-Omni-30B-A3B-Reasoning NVIDIA MoE 30B 0 0 0
Nemotron-Cascade-2-30B-A3B NVIDIA MoE 30B 0 0 0
Nemotron-H-47B-Reasoning-128K NVIDIA Dense 47B 0 0 0
North-Mini-Code-1.0 Cohere - - 0 0 0
NVIDIA-Nemotron-3-Nano-30B-A3B NVIDIA MoE 30B 0 0 0
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 NVIDIA Dense - 0 0 0
NVIDIA-Nemotron-3-Nano-4B NVIDIA Dense 4B 0 0 0
NVIDIA-Nemotron-3-Super-120B-A12B NVIDIA MoE 120B 0 0 0
NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B NVIDIA MoE 75B 0 0 0
OpenReasoning-Nemotron-32B NVIDIA Dense 32B 0 0 0
Qwen-AgentWorld-35B-A3B Qwen (Alibaba) MoE 35B 3 3 0
Qwen2.5-32B-Instruct-AWQ Qwen (Alibaba) Dense 32B 2 0 2
Qwen2.5-72B-Instruct-Q4_K_M.gguf Qwen (Alibaba) Dense 72B 1 1 0
Qwen2.5-Coder-32B-Instruct Qwen (Alibaba) Dense 32B 12 12 0
Qwen3-30B-A3B-Instruct-2507 Qwen (Alibaba) MoE 30B 9 9 0
Qwen3-30B-A3B-Thinking-2507 Qwen (Alibaba) MoE 30B 8 8 0
Qwen3-Coder-30B-A3B-Instruct Qwen (Alibaba) MoE 30B 9 9 0
Qwen3-Coder-Next Qwen (Alibaba) MoE - 4 4 0
Qwen3-Omni-30B-A3B-Thinking Qwen (Alibaba) MoE 30B 1 1 0
Qwen3-VL-30B-A3B-Instruct Qwen (Alibaba) MoE 30B 7 7 0
Qwen3.5-35B-A3B Qwen (Alibaba) MoE 35B 7 7 0
Qwen3.6-27B Qwen (Alibaba) Dense 27B 3 1 2
Qwen3.6-35B-A3B Qwen (Alibaba) MoE 35B 5 5 0
Seed-OSS-36B-Instruct ByteDance Seed - - 0 0 0
Step-3.5-Flash StepFun - - 0 0 0
Tencent-Hy3-295B-A21B Tencent MoE 295B 0 0 0