| Model | Verdict | Decode tok/s | Max ctx | Size | Chat | Coding | |
|---|---|---|---|---|---|---|---|
| Qwen/Qwen3-30B-A3B-Instruct-2507 unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF · IQ4_XS | Fits | 18.67.50–20.5 | 36K | 30.5B | p85 | – | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · Q3_K_M | Fits | 5.604.70–6.40 | 53K | 31.3B | p63 | – | |
| Qwen/Qwen3.5-27B unsloth/Qwen3.5-27B-GGUF · Q4_K_M | Fits | 5.802.30–6.30 | 50K | 27.8B | p60 | p46 | |
| Qwen/Qwen3.8-27B lmstudio-community/Qwen3.8-27B-MLX-4bit · MLX-4BIT | Fits | 6.002.40–6.60 | 39K | 27.8B | p59 | p33 | |
| Qwen/Qwen3.6-27B unsloth/Qwen3.6-27B-GGUF · Q4_K_M | Fits | 5.702.30–6.30 | 48K | 27.8B | p51 | p54 | |
| Qwen/Qwen3.5-35B-A3B bartowski/Qwen_Qwen3.5-35B-A3B-GGUF · IQ3_M | Fits | 36.914.7–40.6 | 40K | 36B | p49 | p35 | |
| google/gemma-4-26B-A4B-it unsloth/gemma-4-26B-A4B-it-GGUF · MXFP4_MOE | Fits | 26.710.7–29.4 | 48K | 25.8B | p49 | – | |
| Qwen/Qwen3.5-9B lmstudio-community/Qwen3.5-9B-MLX-8bit · MLX-8BIT | Fits | 10.04.00–11.0 | 243K | 9.7B | p46 | – | |
| ornith-ai/Ornith-1.5-9B AtomicChat/Ornith-1.5-9B-GGUF · Q8_0 | Fits | 10.84.30–11.9 | 256K | 9.7B | p46 | p24 | |
| Qwen/Qwen3.6-35B-A3B unsloth/Qwen3.6-35B-A3B-GGUF · UD-IQ4_XS | Fits | 36.914.8–40.6 | 44K | 36B | p43 | p41 | |
| openbmb/MiniCPM-V-4.7-35B-A3B openbmb/MiniCPM-V-4.7-35B-A3B-gguf · IQ3_M | Fits | 39.315.7–43.2 | 128K | 35.2B | p42 | – | |
| ornith-ai/Ornith-1.0-35B bartowski/deepreinforce-ai_Ornith-1.0-35B-GGUF · Q3_K_XL | Fits | 37.515.0–41.2 | 43K | 35.1B | – | p40 | |
| openai/gpt-oss-20b unsloth/gpt-oss-20b-GGUF · F16 | Fits | 29.711.9–32.6 | 128K | 21.1B | p39 | p15 | |
| Qwen/Qwen3.5-4B unsloth/Qwen3.5-4B-GGUF · Q8_0 | Fits | 18.37.30–20.2 | 256K | 4.7B | p39 | – | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · Q8_0 | Fits | 6.505.50–7.50 | 256K | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 unsloth/Qwen3-4B-Instruct-2507-GGUF · Q8_0 | Fits | 13.511.5–15.5 | 93K | 4B | p38 | – | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-4bit · MLX-4BIT | Fits | 38.115.2–41.9 | 72K | 32.9B | p37 | p9 | |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 unsloth/Nemotron-3-Nano-30B-A3B-GGUF · Q3_K_S | Fits | 37.715.1–41.5 | 41K | 31.6B | p33 | – | |
| poolside/Laguna-XS-2.1 bartowski/Laguna-XS-2.1-GGUF · Q3_K_XL | Fits | 41.316.5–45.5 | 46K | 33.4B | – | p30 | |
| poolside/Laguna-XS.2 manjunathshiva/Laguna-XS.2-tq3-g64 · MLX-3BIT | Fits | 42.917.1–47.2 | 80K | 33.4B | – | p25 | |
| ornith-ai/Ornith-1.0-9B lmstudio-community/Ornith-1.0-9B-MLX-8bit · MLX-8BIT | Fits | 10.14.00–11.1 | 243K | 9.4B | – | p20 | |
| Qwen/Qwen3-30B-A3B unsloth/Qwen3-30B-A3B-GGUF · IQ4_XS | Fits | 18.67.50–20.5 | 36K | 30.5B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF · IQ4_XS | Fits | 18.67.50–20.5 | 36K | 30.5B | – | – | |
| prism-ml/Bonsai-27B-mlx-1bit MLX-1BIT | Fits | 14.45.80–15.8 | 199K | 26.4B | – | – | |
| ornith-ai/Ornith-1.5-9B-GGUF Q8_0 | Fits | 10.64.30–11.7 | 256K | 9.2B | – | – | |
| prism-ml/Ternary-Bonsai-27B-mlx-2bit MLX-2BIT | Fits | 10.14.00–11.1 | 150K | 26.4B | – | – | |
| Qwen/Qwen2.5-14B-Instruct Qwen/Qwen2.5-14B-Instruct-GGUF · Q6_K | Fits | 6.505.50–7.50 | 32K | 14.8B | – | – | |
| Qwen/Qwen2.5-Coder-14B-Instruct bartowski/Qwen2.5-Coder-14B-Instruct-GGUF · Q6_K_L | Fits | 6.305.40–7.30 | 32K | 14.8B | – | – | |
| Qwen/Qwen3-14B unsloth/Qwen3-14B-GGUF · Q8_0 | Fits | 5.604.80–6.40 | 35K | 14.8B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT wfakhri/OTel-2.0-LLM-31B-IT-GGUF · Q3_K_M | Fits | 5.404.60–6.20 | 43K | 31.3B | – | – | |
| Qwen/Qwen3-32B unsloth/Qwen3-32B-GGUF · Q2_K_L | Fits | 5.404.60–6.20 | 40K | 32.8B | – | – | |
| Qwen/Qwen2.5-Coder-32B-Instruct bartowski/Qwen2.5-Coder-32B-Instruct-GGUF · IQ3_XS | Fits | 5.404.60–6.20 | 32K | 32.8B | – | – | |
| Qwen/Qwen2.5-32B-Instruct bartowski/Qwen2.5-32B-Instruct-GGUF · IQ3_XS | Fits | 5.404.60–6.20 | 32K | 32.8B | – | – |
Quality = benchmark percentile against all indexed models (p50 = median). Speeds are single-user decode ranges.