| Model | Verdict | Decode tok/s | Max ctx | Size | Chat | Coding | |
|---|---|---|---|---|---|---|---|
| Qwen/Qwen3-30B-A3B-Instruct-2507 bartowski/Qwen_Qwen3-30B-A3B-Instruct-2507-GGUF · IQ2_S | Fits | 140119–161 | 195K | 30.5B | p85 | – | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · UD-IQ2_XXS | Fits | 64.354.6–73.9 | 46K | 31.3B | p63 | – | |
| Qwen/Qwen3.5-27B bartowski/Qwen_Qwen3.5-27B-GGUF · IQ2_S | Fits | 56.748.2–65.3 | 38K | 27.8B | p60 | p46 | |
| Qwen/Qwen3.8-27B unsloth/Qwen3.8-27B-GGUF · UD-Q2_K_XL | Fits | 58.850.0–67.7 | 50K | 27.8B | p59 | p33 | |
| Qwen/Qwen3.6-27B unsloth/Qwen3.6-27B-GGUF · UD-IQ2_XXS | Fits | 61.352.1–70.4 | 37K | 27.8B | p51 | p54 | |
| Qwen/Qwen3.5-35B-A3B bartowski/Qwen_Qwen3.5-35B-A3B-GGUF · IQ2_XXS | Fits | 237202–273 | 256K | 36B | p49 | p35 | |
| google/gemma-4-26B-A4B-it unsloth/gemma-4-26B-A4B-it-GGUF · UD-Q2_K_XL | Fits | 217184–249 | 256K | 25.8B | p49 | – | |
| Qwen/Qwen3.5-9B unsloth/Qwen3.5-9B-GGUF · Q8_0 | Fits | 78.066.3–89.7 | 92K | 9.7B | p46 | – | |
| ornith-ai/Ornith-1.5-9B AtomicChat/Ornith-1.5-9B-GGUF · Q8_0 | Fits | 78.066.3–89.7 | 92K | 9.7B | p46 | p24 | |
| Qwen/Qwen3.6-35B-A3B unsloth/Qwen3.6-35B-A3B-GGUF · UD-IQ2_XXS | Fits | 237201–272 | 256K | 36B | p43 | p41 | |
| openbmb/MiniCPM-V-4.7-35B-A3B AtomicChat/MiniCPM-V-4.7-35B-A3B-GGUF · IQ1_M | Fits | 240204–276 | 256K | 35.2B | p42 | – | |
| ornith-ai/Ornith-1.0-35B bartowski/deepreinforce-ai_Ornith-1.0-35B-GGUF · IQ2_S | Fits | 235200–271 | 256K | 35.1B | – | p40 | |
| Qwen/Qwen3.5-4B BF16 | Fits | 72.729.1–79.9 | 66K | 4.7B | p39 | – | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · Q6_K | Fits | 64.955.2–74.7 | 77K | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 unsloth/Qwen3-4B-Instruct-2507-GGUF · Q8_0 | Fits | 10690.3–122 | 49K | 4B | p38 | – | |
| poolside/Laguna-XS-2.1 bartowski/Laguna-XS-2.1-GGUF · IQ2_XS | Fits | 233198–268 | 256K | 33.4B | – | p30 | |
| poolside/Laguna-XS.2 poolside-laguna-hackathon/Piscina-XS.2-GGUF · IQ1 | Fits | 242205–278 | 256K | 33.4B | – | p25 | |
| ornith-ai/Ornith-1.0-9B unsloth/Ornith-1.0-9B-GGUF · Q8_0 | Fits | 78.266.5–89.9 | 92K | 9.4B | – | p20 | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF · UD-IQ1_M | Fits | 138117–159 | 195K | 30.5B | – | – | |
| Qwen/Qwen3-30B-A3B unsloth/Qwen3-30B-A3B-GGUF · UD-IQ1_M | Fits | 138117–159 | 40K | 30.5B | – | – | |
| prism-ml/Bonsai-27B-mlx-1bit MLX-1BIT | Fits | 86.834.7–95.5 | 93K | 26.4B | – | – | |
| ornith-ai/Ornith-1.5-9B-GGUF Q8_0 | Fits | 76.464.9–87.8 | 84K | 9.2B | – | – | |
| Qwen/Qwen3-14B unsloth/Qwen3-14B-GGUF · Q4_K_M | Fits | 66.156.2–76.0 | 33K | 14.8B | – | – | |
| prism-ml/Ternary-Bonsai-27B-mlx-2bit MLX-2BIT | Fits | 65.426.2–71.9 | 44K | 26.4B | – | – | |
| Qwen/Qwen2.5-Coder-14B-Instruct bartowski/Qwen2.5-Coder-14B-Instruct-GGUF · Q4_K_S | Fits | 63.854.2–73.4 | 32K | 14.8B | – | – | |
| Qwen/Qwen2.5-14B-Instruct bartowski/Qwen2.5-14B-Instruct-GGUF · Q4_K_S | Fits | 63.854.2–73.4 | 32K | 14.8B | – | – | |
| openai/gpt-oss-20b unsloth/gpt-oss-20b-GGUF · F16 | Offload | 85.842.9–129 | 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 | 27.313.7–41.0 | 256K | 32.9B | p37 | p9 | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 MIXED_PRECISION | Offload | 53.721.5–80.5 | 1M | 47.1B | p36 | p9 | |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 unsloth/Nemotron-3-Nano-30B-A3B-GGUF · Q5_K_M | Offload | 41.020.5–61.4 | 256K | 31.6B | p33 | – | |
| ornith-ai/Ornith-1.5-35B-A3B-NVFP4 MIXED_PRECISION | Offload | 64.725.9–97.0 | 256K | 34B | – | – | |
| nvidia/Qwen3.6-35B-A3B-NVFP4 MIXED_PRECISION | Offload | 64.625.9–97.0 | 256K | 34B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 FP8 | Offload | 21.58.60–32.3 | 97K | 30.5B | – | – | |
| Qwen/Qwen3-32B unsloth/Qwen3-32B-GGUF · Q2_K_L | Offload | 3.301.70–5.00 | 0 | 32.8B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT wfakhri/OTel-2.0-LLM-31B-IT-GGUF · Q4_K_S | Offload | 3.001.50–4.40 | 0 | 31.3B | – | – | |
| Qwen/Qwen2.5-Coder-32B-Instruct bartowski/Qwen2.5-Coder-32B-Instruct-GGUF · IQ3_XS | Offload | 3.001.50–4.50 | 0 | 32.8B | – | – | |
| Qwen/Qwen2.5-32B-Instruct bartowski/Qwen2.5-32B-Instruct-GGUF · IQ3_XS | Offload | 3.001.50–4.50 | 0 | 32.8B | – | – |
Quality = benchmark percentile against all indexed models (p50 = median). Speeds are single-user decode ranges.