| Model | Verdict | Decode tok/s | Max ctx | Size | Chat | Coding | |
|---|---|---|---|---|---|---|---|
| Qwen/Qwen3-30B-A3B-Instruct-2507 unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF · Q5_K_M | Fits | 27.010.8–29.7 | 33K | 30.5B | p85 | – | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · Q5_K_M | Fits | 5.404.60–6.20 | 43K | 31.3B | p63 | – | |
| Qwen/Qwen3.5-27B unsloth/Qwen3.5-27B-GGUF · Q6_K | Fits | 5.802.30–6.40 | 43K | 27.8B | p60 | p46 | |
| Qwen/Qwen3.8-27B lmstudio-community/Qwen3.8-27B-MLX-6bit · MLX-6BIT | Fits | 5.702.30–6.30 | 38K | 27.8B | p59 | p33 | |
| Qwen/Qwen3.6-27B unsloth/Qwen3.6-27B-GGUF · Q6_K | Fits | 5.802.30–6.40 | 42K | 27.8B | p51 | p54 | |
| Qwen/Qwen3.5-35B-A3B unsloth/Qwen3.5-35B-A3B-GGUF · Q4_K_M | Fits | 49.019.6–54.0 | 134K | 36B | p49 | p35 | |
| google/gemma-4-26B-A4B-it unsloth/gemma-4-26B-A4B-it-GGUF · MXFP4_MOE | Fits | 38.015.2–41.9 | 256K | 25.8B | p49 | – | |
| Qwen/Qwen3.5-9B lmstudio-community/Qwen3.5-9B-MLX-8bit · MLX-8BIT | Fits | 12.95.20–14.2 | 256K | 9.7B | p46 | – | |
| ornith-ai/Ornith-1.5-9B AtomicChat/Ornith-1.5-9B-GGUF · Q8_0 | Fits | 13.95.60–15.3 | 256K | 9.7B | p46 | p24 | |
| Qwen/Qwen3.6-35B-A3B unsloth/Qwen3.6-35B-A3B-MTP-GGUF · MXFP4_MOE | Fits | 48.819.5–53.7 | 126K | 36B | p43 | p41 | |
| openbmb/MiniCPM-V-4.7-35B-A3B openbmb/MiniCPM-V-4.7-35B-A3B-gguf · Q5_K_S | Fits | 46.918.8–51.6 | 45K | 35.2B | p42 | – | |
| ornith-ai/Ornith-1.0-35B bartowski/deepreinforce-ai_Ornith-1.0-35B-GGUF · Q5_K_S | Fits | 46.718.7–51.4 | 37K | 35.1B | – | p40 | |
| openai/gpt-oss-20b lmstudio-community/gpt-oss-20b-MLX-8bit · MLX-8BIT | Fits | 26.810.7–29.5 | 107K | 21.1B | p39 | p15 | |
| Qwen/Qwen3.5-4B unsloth/Qwen3.5-4B-GGUF · Q8_0 | Fits | 23.79.50–26.1 | 256K | 4.7B | p39 | – | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · Q8_0 | Fits | 9.207.80–10.6 | 256K | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 unsloth/Qwen3-4B-Instruct-2507-GGUF · Q8_0 | Fits | 18.015.3–20.7 | 138K | 4B | p38 | – | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF · MXFP4_MOE | Fits | 43.417.3–47.7 | 236K | 32.9B | p37 | p9 | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 MIXED_PRECISION | Fits | 44.717.9–49.1 | 449K | 47.1B | p36 | p9 | |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 unsloth/Nemotron-3-Nano-30B-A3B-GGUF · Q4_K_M | Fits | 41.816.7–45.9 | 58K | 31.6B | p33 | – | |
| poolside/Laguna-XS-2.1 bartowski/Laguna-XS-2.1-GGUF · Q5_K_L | Fits | 45.318.1–49.8 | 34K | 33.4B | – | p30 | |
| poolside/Laguna-XS.2 Lucebox/Laguna-XS.2-GGUF · Q4_K_M | Fits | 49.619.8–54.6 | 109K | 33.4B | – | p25 | |
| ornith-ai/Ornith-1.0-9B lmstudio-community/Ornith-1.0-9B-MLX-8bit · MLX-8BIT | Fits | 12.95.20–14.2 | 256K | 9.4B | – | p20 | |
| ornith-ai/Ornith-1.5-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 47.719.1–52.5 | 71K | 34B | – | – | |
| nvidia/Qwen3.6-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 47.719.1–52.5 | 71K | 34B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 ijohn07/Qwen3-Coder-30B-A3B-Instruct-FP8-Q4_K_M-GGUF · Q4_K_M | Fits | 28.711.5–31.6 | 64K | 30.5B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-5bit · MLX-5BIT | Fits | 27.411.0–30.1 | 40K | 30.5B | – | – | |
| Qwen/Qwen3-30B-A3B unsloth/Qwen3-30B-A3B-GGUF · Q5_K_M | Fits | 27.010.8–29.7 | 33K | 30.5B | – | – | |
| prism-ml/Bonsai-27B-mlx-1bit MLX-1BIT | Fits | 19.77.90–21.7 | 256K | 26.4B | – | – | |
| ornith-ai/Ornith-1.5-9B-GGUF Q8_0 | Fits | 13.75.50–15.1 | 256K | 9.2B | – | – | |
| prism-ml/Ternary-Bonsai-27B-mlx-2bit MLX-2BIT | Fits | 13.55.40–14.8 | 248K | 26.4B | – | – | |
| Qwen/Qwen3-14B lmstudio-community/Qwen3-14B-MLX-8bit · MLX-8BIT | Fits | 7.402.90–8.10 | 40K | 14.8B | – | – | |
| Qwen/Qwen2.5-14B-Instruct Qwen/Qwen2.5-14B-Instruct-GGUF · Q8_0 | Fits | 7.106.10–8.20 | 32K | 14.8B | – | – | |
| Qwen/Qwen2.5-Coder-14B-Instruct Qwen/Qwen2.5-Coder-14B-Instruct-GGUF · Q4_K_M | Fits | 6.405.40–7.40 | 32K | 14.8B | – | – | |
| RadixArk/Qwen3.8-27B-NVFP4 MIXED_PRECISION | Fits | 6.002.40–6.60 | 51K | 26.4B | – | – | |
| Qwen/Qwen2.5-32B-Instruct Qwen/Qwen2.5-32B-Instruct-GGUF · Q4_K_M | Fits | 5.504.60–6.30 | 32K | 32.8B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT wfakhri/OTel-2.0-LLM-31B-IT-GGUF · Q5_K_M | Fits | 5.404.60–6.20 | 39K | 31.3B | – | – | |
| Qwen/Qwen3-32B unsloth/Qwen3-32B-GGUF · Q4_K_M | Fits | 5.404.60–6.20 | 40K | 32.8B | – | – | |
| Qwen/Qwen2.5-Coder-32B-Instruct bartowski/Qwen2.5-Coder-32B-Instruct-GGUF · Q4_K_L | Fits | 5.304.50–6.10 | 32K | 32.8B | – | – |
Quality = benchmark percentile against all indexed models (p50 = median). Speeds are single-user decode ranges.