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 familyAllArceeBaichuanBTLCohereDeepseekDeepseek-CoderDeepseek-R1DeepSeek-V4.1-FlashGemmaGLMGptHunyuanKimiKwaipilotLagunaLFMLingLlamaMiniCPM-VMinimaxMistralMobileLLMMuseNemotronOrnithPhiQwenQwen3.8RNJSparkunknown
| Model | Family | <24GB | 24–48GB | >48GB | runs |
|---|---|---|---|---|---|
| Qwen3.8-27B | Qwen | 391.0 · NVFP4 | 4546.8 · NVFP4 | 1392.4 · W4A16 | 67 |
| Qwen3.8-Flash-Next | Qwen | 81.8 · Q2_0 | 145.8 · W4A16+FP8-KV | 204.5 · FP8_E4M3 | 40 |
| Qwen3.6-35B-A3B | Qwen | 129.4 · UD-Q4_K_XL | 969.4 · MQ4R | 330.2 · NVFP4 | 17 |
| Qwen3.6-27B | Qwen | 60.6 · IQ4_XS | 240.8 · AutoRound INT4 | 101.4 · FP8 | 11 |
| Ornith-1.5-35B-A3B | Qwen | 64.4 · Q4_K_M | 258.8 · NVFP4 | 87.1 · Q8_0 | 9 |
| Qwen 3.8 Flash | Qwen | — | — | 86.8 · EXL3 3.05bpw | 8 |
| Ornith-1.5-9B | Qwen | 102.0 · Q4_K_M | 49.6 · Q8_0 | 61.5 · BF16 | 8 |
| Qwen3.8-27B-MTP | Qwen | — | 117.7 · NVFP4 | 112.1 · NVFP4 | 7 |
| Qwen3.5-0.8B | Qwen | 545.3 · MQ4 | 554.5 · MQ4 | — | 5 |
| Qwen3.8-Flash-Next-hibrid48 | Qwen | — | — | 474.0 · NVFP4 (output head) | 5 |
| Qwen3.8-27B-Uncensored | Qwen | 74.1 · IQ2_XXS | 136.4 · GPTQ-Int4 | — | 4 |
| Qwen3.6-27B-MTP | Qwen | — | 41.2 · Q4_K_M | 60.1 · Q6_K | 4 |
| Qwen3-14B | Qwen | 75.0 · Q4_K_M | — | 90.8 · FP8 | 3 |
| Qwen3.8-9B-Distill | Qwen | 76.4 · Q4_K_M | — | — | 3 |
| Ornith-1.0-9B | Qwen | 52.5 · Q4_K_M | 31.2 · BF16 | — | 2 |
| Bonsai-27B | Qwen | 72.9 · Q1_0 | 136.7 · Q1_0 | — | 2 |
| Qwen3-30B-A3B-Instruct-2507 | Qwen | — | 312.9 · Q4_K_M | — | 2 |
| Qwen3-0.6B | Qwen | 310.4 · Q8_0 | — | 956.4 · Q4_K_M | 2 |
| Qwen3-4B | Qwen | — | 80.2 · Q4_K_M | — | 2 |
| Qwen3.5-27B | Qwen | — | 286.6 · MQ4-AWQ | — | 2 |
| QUEST-30B-RL-B70-Turbo | Qwen | — | 94.6 · Q5_K_M | — | 2 |
| Ternary Bonsai 2 27B | Qwen3.8 | — | — | — | 2 |
| Ornith-1.5-35B-A3B-MTP | Qwen | 55.3 · Q4_K_M | — | 33.2 · FP8 | 2 |
| Qwen3.5-9B | Qwen | 51.9 · Q4_K_M | 38.6 · bfp_bf4 | — | 2 |
| Qwen3-Coder-30B-A3B-Instruct | Qwen | — | 263.0 · Q6_K | 26.1 · FP8 | 2 |
| Qwen3.6-35B-A3B-MTP | Qwen | — | 222.9 · Unsloth-Dynamic-IQ4_XS | — | 2 |
| KAT-Coder-V2.5-Dev-AWQ-W4A16-ASYM | Qwen | — | 201.2 · W4A16 | — | 1 |
| Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP | Qwen | — | 283.1 · NVFP4 | — | 1 |
| Huihui-Qwen3.8-27B-abliterated | Qwen | — | 117.7 · NVFP4 | — | 1 |
| Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved | Qwen | — | 25.4 · GPTQ | — | 1 |
| Qwen3.8-27B-Fable-Distill | Qwen | — | 198.8 · Q4_K_M | — | 1 |
| Qwen3.8-27B-5090-goldilocks | Qwen | — | 93.5 · Q6_K | — | 1 |
| Qwythos-9B-v2 | Qwen | 51.1 · Q4_K_M | — | — | 1 |
| Qwen3.5-35B-A3B | Qwen | — | 209.3 · Q4_K_M | — | 1 |
| Qwen3-4B-Thinking-2507 | Qwen | — | 219.7 · Q8_0 | — | 1 |
| Qwen2.5-VL-7B-Instruct | Qwen | — | 222.4 · Q4_K_S | — | 1 |
| Qwen3.5-4B | Qwen | 78.6 · Q4_K_M | — | — | 1 |
| Qwen3.8-27B-Ridge | Qwen | 9.0 · Ridge-3.7bpw | — | — | 1 |
| Ornith-1.5-35B-A3B-GPTQ-Int4-sym-G128-MTP-BF16-MixedCal-v2 | Qwen | — | 108.4 · GPTQ-Int4 | — | 1 |
| Unsloth-Ornith-1.5-35B-A3B | Qwen | 53.3 · Q2_K_XL | — | — | 1 |