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
GLM-5.3-Flash	GLM	—	250.6 · compressed-tensors	264.6 · W4A16	21
GLM-4.7-Flash	GLM	—	182.5 · Q4_K_M	—	2
GLM-5.2	GLM	—	—	29.7 · INT4-INT8-Mix	1
GLM-4.6V-Flash	GLM	—	132.7 · Q8_0	—	1
GLM-Z1-32B-0414	GLM	16.6 · Q4_K_M	—	—	1

26 runs · last run Oct 12, 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