| Model | Verdict | Decode tok/s | Max ctx | Size | Chat | Coding | |
|---|---|---|---|---|---|---|---|
| Qwen/Qwen3.8-27B unsloth/Qwen3.8-27B-GGUF · UD-IQ1_S | Fits | 36.214.5–39.8 | 33K | 27.8B | p59 | p33 | |
| Qwen/Qwen3.6-27B prism-ml/Ternary-Bonsai-27B-gguf · BF16 | Fits | 32.312.9–35.5 | 35K | 27.8B | p51 | p54 | |
| Qwen/Qwen3.5-9B unsloth/Qwen3.5-9B-GGUF · Q6_K | Fits | 36.014.4–39.6 | 33K | 9.7B | p46 | – | |
| ornith-ai/Ornith-1.5-9B AtomicChat/Ornith-1.5-9B-GGUF · Q6_K | Fits | 36.414.5–40.0 | 37K | 9.7B | p46 | p24 | |
| Qwen/Qwen3.5-4B unsloth/Qwen3.5-4B-GGUF · Q8_0 | Fits | 48.519.4–53.4 | 81K | 4.7B | p39 | – | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · IQ4_NL | Fits | 33.213.3–36.5 | 36K | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 unsloth/Qwen3-4B-Instruct-2507-GGUF · Q8_0 | Fits | 37.515.0–41.3 | 37K | 4B | p38 | – | |
| ornith-ai/Ornith-1.0-9B unsloth/Ornith-1.0-9B-GGUF · Q6_K | Fits | 36.014.4–39.6 | 32K | 9.4B | – | p20 | |
| ornith-ai/Ornith-1.5-9B-GGUF Q5_K_M | Fits | 39.615.8–43.6 | 39K | 9.2B | – | – | |
| Qwen/Qwen3-14B unsloth/Qwen3-14B-GGUF · UD-IQ2_XXS | Fits | 36.214.5–39.8 | 34K | 14.8B | – | – | |
| prism-ml/Bonsai-27B-mlx-1bit MLX-1BIT | Tight fit | 41.316.5–45.4 | 30K | 26.4B | – | – | |
| Qwen/Qwen3-30B-A3B-Instruct-2507 unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF · Q8_0 | Offload | 15.57.80–23.3 | 55K | 30.5B | p85 | – | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · UD-IQ3_XXS | Offload | 3.201.60–4.90 | 0 | 31.3B | p63 | – | |
| Qwen/Qwen3.5-27B unsloth/Qwen3.5-27B-GGUF · Q3_K_M | Offload | 3.301.30–4.90 | 0 | 27.8B | p60 | p46 | |
| Qwen/Qwen3.5-35B-A3B unsloth/Qwen3.5-35B-A3B-GGUF · Q8_0 | Offload | 27.110.8–40.7 | 237K | 36B | p49 | p35 | |
| google/gemma-4-26B-A4B-it unsloth/gemma-4-26B-A4B-it-GGUF · Q8_0 | Offload | 20.010.0–30.0 | 211K | 25.8B | p49 | – | |
| Qwen/Qwen3.6-35B-A3B unsloth/Qwen3.6-35B-A3B-MTP-GGUF · Q8_0 | Offload | 26.610.6–39.8 | 235K | 36B | p43 | p41 | |
| openbmb/MiniCPM-V-4.7-35B-A3B openbmb/MiniCPM-V-4.7-35B-A3B-gguf · Q8_0 | Offload | 27.110.9–40.7 | 237K | 35.2B | p42 | – | |
| ornith-ai/Ornith-1.0-35B unsloth/Ornith-1.0-35B-GGUF · Q8_0 | Offload | 27.110.9–40.7 | 237K | 35.1B | – | p40 | |
| openai/gpt-oss-20b MXFP4 | Offload | 11.64.70–17.5 | 128K | 21.1B | p39 | p15 | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF · Q8_0 | Offload | 21.08.40–31.5 | 256K | 32.9B | p37 | p9 | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 MIXED_PRECISION | Offload | 35.014.0–52.5 | 698K | 47.1B | p36 | p9 | |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 unsloth/Nemotron-3-Nano-30B-A3B-GGUF · Q8_0 | Offload | 21.88.70–32.7 | 256K | 31.6B | p33 | – | |
| poolside/Laguna-XS-2.1 bartowski/Laguna-XS-2.1-GGUF · Q8_0 | Offload | 27.113.6–40.7 | 129K | 33.4B | – | p30 | |
| poolside/Laguna-XS.2 poolside-laguna-hackathon/Laguna-XS.2-GGUF · Q4_K_M | Offload | 15.57.70–23.2 | 75K | 33.4B | – | p25 | |
| ornith-ai/Ornith-1.5-35B-A3B-NVFP4 MIXED_PRECISION | Offload | 41.716.7–62.6 | 245K | 34B | – | – | |
| nvidia/Qwen3.6-35B-A3B-NVFP4 MIXED_PRECISION | Offload | 41.716.7–62.6 | 245K | 34B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 FP8 | Offload | 16.16.40–24.1 | 52K | 30.5B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF · Q8_0 | Offload | 15.57.80–23.3 | 55K | 30.5B | – | – | |
| Qwen/Qwen3-30B-A3B unsloth/Qwen3-30B-A3B-GGUF · Q8_0 | Offload | 15.57.80–23.3 | 40K | 30.5B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT wfakhri/OTel-2.0-LLM-31B-IT-GGUF · Q2_K | Offload | 3.201.60–4.90 | 0 | 31.3B | – | – | |
| Qwen/Qwen3-32B unsloth/Qwen3-32B-GGUF · Q2_K | Offload | 3.001.50–4.40 | 0 | 32.8B | – | – | |
| Qwen/Qwen2.5-Coder-32B-Instruct bartowski/Qwen2.5-Coder-32B-Instruct-GGUF · Q2_K | Offload | 3.001.50–4.50 | 0 | 32.8B | – | – | |
| Qwen/Qwen2.5-32B-Instruct Qwen/Qwen2.5-32B-Instruct-GGUF · Q2_K | Offload | 3.001.50–4.50 | 0 | 32.8B | – | – | |
| Qwen/Qwen2.5-Coder-14B-Instruct bartowski/Qwen2.5-Coder-14B-Instruct-GGUF · Q5_K_M | Offload | 3.001.50–4.50 | 0 | 14.8B | – | – | |
| Qwen/Qwen2.5-14B-Instruct Qwen/Qwen2.5-14B-Instruct-GGUF · Q5_K_M | Offload | 3.001.50–4.50 | 0 | 14.8B | – | – |
Quality = benchmark percentile against all indexed models (p50 = median). Speeds are single-user decode ranges.