Compatibility Matrix

Best community run per VRAM tier for the most-run open-weight models. Cells show tok/s and quantization — the same model often lands in multiple tiers via different quants. Full board · Submit your run.

Model familyAll Arcee Baichuan BTL Cohere Deepseek Deepseek-Coder Deepseek-R1 DeepSeek-V4.1-Flash Gemma GLM Gpt Hunyuan Kimi Kwaipilot Laguna LFM Ling Llama MiniCPM-V Minimax Mistral MobileLLM Muse Nemotron Ornith Phi Qwen Qwen3.8 RNJ Spark unknown

Model	Family	<24GB	24–48GB	>48GB	runs
LFM2.5-350M	LFM	437.7 · MQ4	466.0 · MQ4	—	5
LFM2.5-230M	LFM	481.8 · MQ4	520.0 · MQ4	—	3
LFM2.5-8B-A1B	LFM	277.8 · Q6_K	241.1 · MQ4	—	2
LFM2-350M	LFM	—	2231.4 · NVFP4	—	1
LFM2-8B-A1B	LFM	18.3 · Q4_K_M	—	—	1

12 runs · last run Sep 4, 2026. Filter by family above; full board for every row.

VRAM tiers: <24 GB · 24–48 GB · >48 GB. A cell shows the best single-stream tok/s and quant recorded in that tier — not a guarantee for every loadout. Imported rows carry their original methodology link.

Related guides: best GPU for Qwen3 · quantization · Strix Halo 128GB