moonshotai/Kimi-K2.5

Image-Text-to-Text • 1.1T • Updated 17 days ago • 2.89M • • 2.29k

Note 1st for creative writing tasks; not evaluated on productivity tasks due to local inference speed constraints

deepseek-ai/DeepSeek-V3-0324

Text Generation • 685B • Updated Mar 27, 2025 • 326k • • 3.09k

Note 3rd for creative writing tasks, a classic

deepseek-ai/DeepSeek-R1-0528

Text Generation • 685B • Updated May 29, 2025 • 1.06M • • 2.41k

Note 2nd for creative writing tasks, a classic

MiniMaxAI/MiniMax-M2.5

Text Generation • 229B • Updated 6 days ago • 533k • • 1.21k

Note Agentic coding tasks

Qwen/Qwen3.5-397B-A17B

Image-Text-to-Text • 403B • Updated 1 day ago • 1.75M • • 1.34k

Note General productivity tasks - vision + relatively fast for its size on CPU+GPU

Qwen/Qwen3.5-122B-A10B

Image-Text-to-Text • 125B • Updated 15 days ago • 455k • • 438

Note General productivity tasks - vision + speedy performance on a single 96gb GPU, weaker coding capabilities than Minimax

Doctor-Shotgun/ML2-123B-Magnum-Diamond

Text Generation • 123B • Updated Jul 7, 2025 • 12 • 11

Note Legacy model for creative writing tasks (96gb VRAM)

Doctor-Shotgun/L3.3-70B-Magnum-Diamond

Text Generation • 71B • Updated Jun 25, 2025 • 56 • 5

Note Legacy model for creative writing tasks (48gb VRAM)

Doctor-Shotgun/MS3.2-24B-Magnum-Diamond

Text Generation • 24B • Updated Jul 7, 2025 • 346 • 55

Note Legacy model for creative writing tasks (24gb VRAM)