| 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 | 24.69.80–27.0 | 33K | 30.5B | p85 | – | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · Q5_K_M | Fits | 6.605.60–7.60 | 43K | 31.3B | p63 | – | |
| Qwen/Qwen3.5-27B unsloth/Qwen3.5-27B-GGUF · Q6_K | Fits | 7.202.90–8.00 | 43K | 27.8B | p60 | p46 | |
| Qwen/Qwen3.8-27B lmstudio-community/Qwen3.8-27B-MLX-6bit · MLX-6BIT | Fits | 7.102.90–7.90 | 38K | 27.8B | p59 | p33 | |
| Qwen/Qwen3.6-27B unsloth/Qwen3.6-27B-GGUF · Q6_K | Fits | 7.202.90–7.90 | 42K | 27.8B | p51 | p54 | |
| Qwen/Qwen3.5-35B-A3B unsloth/Qwen3.5-35B-A3B-GGUF · Q4_K_M | Fits | 46.818.7–51.5 | 134K | 36B | p49 | p35 | |
| google/gemma-4-26B-A4B-it unsloth/gemma-4-26B-A4B-it-GGUF · MXFP4_MOE | Fits | 38.415.3–42.2 | 256K | 25.8B | p49 | – | |
| Qwen/Qwen3.5-9B lmstudio-community/Qwen3.5-9B-MLX-8bit · MLX-8BIT | Fits | 16.06.40–17.6 | 256K | 9.7B | p46 | – | |
| ornith-ai/Ornith-1.5-9B AtomicChat/Ornith-1.5-9B-GGUF · Q8_0 | Fits | 17.36.90–19.0 | 256K | 9.7B | p46 | p24 | |
| Qwen/Qwen3.6-35B-A3B unsloth/Qwen3.6-35B-A3B-MTP-GGUF · MXFP4_MOE | Fits | 46.618.7–51.3 | 126K | 36B | p43 | p41 | |
| openbmb/MiniCPM-V-4.7-35B-A3B openbmb/MiniCPM-V-4.7-35B-A3B-gguf · Q5_K_S | Fits | 45.318.1–49.8 | 45K | 35.2B | p42 | – | |
| ornith-ai/Ornith-1.0-35B bartowski/deepreinforce-ai_Ornith-1.0-35B-GGUF · Q5_K_S | Fits | 45.118.0–49.6 | 37K | 35.1B | – | p40 | |
| openai/gpt-oss-20b lmstudio-community/gpt-oss-20b-MLX-8bit · MLX-8BIT | Fits | 32.312.9–35.5 | 107K | 21.1B | p39 | p15 | |
| Qwen/Qwen3.5-4B unsloth/Qwen3.5-4B-GGUF · Q8_0 | Fits | 28.411.4–31.2 | 256K | 4.7B | p39 | – | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · Q8_0 | Fits | 10.08.50–11.5 | 256K | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 BF16 | Fits | 14.512.3–16.7 | 116K | 4B | p38 | – | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 bartowski/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF · Q5_K_S | Fits | 44.717.9–49.2 | 33K | 32.9B | p37 | p9 | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 MIXED_PRECISION | Fits | 47.619.0–52.3 | 449K | 47.1B | p36 | p9 | |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 unsloth/Nemotron-3-Nano-30B-A3B-GGUF · Q4_K_M | Fits | 45.018.0–49.5 | 58K | 31.6B | p33 | – | |
| poolside/Laguna-XS-2.1 bartowski/Laguna-XS-2.1-GGUF · Q5_K_L | Fits | 50.220.1–55.3 | 34K | 33.4B | – | p30 | |
| poolside/Laguna-XS.2 Lucebox/Laguna-XS.2-GGUF · Q4_K_M | Fits | 54.321.7–59.7 | 109K | 33.4B | – | p25 | |
| ornith-ai/Ornith-1.0-9B lmstudio-community/Ornith-1.0-9B-MLX-8bit · MLX-8BIT | Fits | 16.16.40–17.7 | 256K | 9.4B | – | p20 | |
| ornith-ai/Ornith-1.5-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 45.818.3–50.4 | 71K | 34B | – | – | |
| nvidia/Qwen3.6-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 45.818.3–50.4 | 71K | 34B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 ijohn07/Qwen3-Coder-30B-A3B-Instruct-FP8-Q4_K_M-GGUF · Q4_K_M | Fits | 25.610.3–28.2 | 64K | 30.5B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-5bit · MLX-5BIT | Fits | 24.89.90–27.3 | 40K | 30.5B | – | – | |
| Qwen/Qwen3-30B-A3B unsloth/Qwen3-30B-A3B-GGUF · Q5_K_M | Fits | 24.69.80–27.0 | 33K | 30.5B | – | – | |
| prism-ml/Bonsai-27B-mlx-1bit MLX-1BIT | Fits | 21.98.80–24.1 | 256K | 26.4B | – | – | |
| ornith-ai/Ornith-1.5-9B-GGUF Q8_0 | Fits | 17.06.80–18.7 | 256K | 9.2B | – | – | |
| prism-ml/Ternary-Bonsai-27B-mlx-2bit MLX-2BIT | Fits | 15.76.30–17.3 | 248K | 26.4B | – | – | |
| Qwen/Qwen3-14B lmstudio-community/Qwen3-14B-MLX-8bit · MLX-8BIT | Fits | 9.003.60–9.90 | 40K | 14.8B | – | – | |
| Qwen/Qwen2.5-14B-Instruct Qwen/Qwen2.5-14B-Instruct-GGUF · Q8_0 | Fits | 8.707.40–10.0 | 32K | 14.8B | – | – | |
| Qwen/Qwen2.5-Coder-14B-Instruct Qwen/Qwen2.5-Coder-14B-Instruct-GGUF · Q4_K_M | Fits | 7.806.70–9.00 | 32K | 14.8B | – | – | |
| RadixArk/Qwen3.8-27B-NVFP4 MIXED_PRECISION | Fits | 7.403.00–8.10 | 51K | 26.4B | – | – | |
| Qwen/Qwen2.5-32B-Instruct Qwen/Qwen2.5-32B-Instruct-GGUF · Q4_K_M | Fits | 6.605.60–7.60 | 32K | 32.8B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT wfakhri/OTel-2.0-LLM-31B-IT-GGUF · Q5_K_M | Fits | 6.505.60–7.50 | 39K | 31.3B | – | – | |
| Qwen/Qwen2.5-Coder-32B-Instruct bartowski/Qwen2.5-Coder-32B-Instruct-GGUF · Q4_K_L | Fits | 6.505.50–7.50 | 32K | 32.8B | – | – | |
| Qwen/Qwen3-32B unsloth/Qwen3-32B-GGUF · Q4_K_M | Fits | 6.305.40–7.30 | 40K | 32.8B | – | – |
Quality = benchmark percentile against all indexed models (p50 = median). Speeds are single-user decode ranges.