| Model | Verdict | Decode tok/s | Max ctx | Size | Chat | Coding | |
|---|---|---|---|---|---|---|---|
| Qwen/Qwen3-30B-A3B-Instruct-2507 unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF · Q4_K_S | Fits | 98.283.4–113 | 256K | 30.5B | p85 | – | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · Q4_K_S | Fits | 27.623.5–31.8 | 41K | 31.3B | p63 | – | |
| Qwen/Qwen3.5-27B unsloth/Qwen3.5-27B-GGUF · Q5_K_M | Fits | 26.322.4–30.3 | 35K | 27.8B | p60 | p46 | |
| Qwen/Qwen3.8-27B unsloth/Qwen3.8-27B-GGUF · Q4_1 | Fits | 28.924.6–33.2 | 49K | 27.8B | p59 | p33 | |
| Qwen/Qwen3.6-27B unsloth/Qwen3.6-27B-GGUF · Q5_K_M | Fits | 26.422.5–30.4 | 37K | 27.8B | p51 | p54 | |
| Qwen/Qwen3.5-35B-A3B bartowski/Qwen_Qwen3.5-35B-A3B-GGUF · IQ4_XS | Fits | 167142–192 | 256K | 36B | p49 | p35 | |
| google/gemma-4-26B-A4B-it unsloth/gemma-4-26B-A4B-it-GGUF · MXFP4_MOE | Fits | 143122–165 | 256K | 25.8B | p49 | – | |
| Qwen/Qwen3.5-9B unsloth/Qwen3.5-9B-GGUF · Q8_0 | Fits | 57.448.8–66.0 | 256K | 9.7B | p46 | – | |
| ornith-ai/Ornith-1.5-9B AtomicChat/Ornith-1.5-9B-GGUF · Q8_0 | Fits | 57.448.8–66.0 | 256K | 9.7B | p46 | p24 | |
| Qwen/Qwen3.6-35B-A3B unsloth/Qwen3.6-35B-A3B-GGUF · UD-IQ4_NL_XL | Fits | 168143–194 | 256K | 36B | p43 | p41 | |
| openbmb/MiniCPM-V-4.7-35B-A3B openbmb/MiniCPM-V-4.7-35B-A3B-gguf · IQ4_NL | Fits | 167142–192 | 256K | 35.2B | p42 | – | |
| ornith-ai/Ornith-1.0-35B bartowski/deepreinforce-ai_Ornith-1.0-35B-GGUF · IQ4_XS | Fits | 171145–197 | 256K | 35.1B | – | p40 | |
| openai/gpt-oss-20b unsloth/gpt-oss-20b-GGUF · F16 | Fits | 154131–178 | 128K | 21.1B | p39 | p15 | |
| Qwen/Qwen3.5-4B unsloth/Qwen3.5-4B-GGUF · Q8_0 | Fits | 94.079.9–108 | 256K | 4.7B | p39 | – | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · Q8_0 | Fits | 38.532.7–44.3 | 256K | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 unsloth/Qwen3-4B-Instruct-2507-GGUF · Q8_0 | Fits | 77.565.8–89.1 | 105K | 4B | p38 | – | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 bartowski/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF · Q3_K_M | Fits | 144123–166 | 256K | 32.9B | p37 | p9 | |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 unsloth/Nemotron-3-Nano-30B-A3B-GGUF · IQ4_NL | Fits | 150128–173 | 256K | 31.6B | p33 | – | |
| poolside/Laguna-XS-2.1 bartowski/Laguna-XS-2.1-GGUF · IQ4_NL | Fits | 167142–192 | 256K | 33.4B | – | p30 | |
| poolside/Laguna-XS.2 poolside-laguna-hackathon/Piscina-XS.2-GGUF · IQ2 | Fits | 193164–222 | 256K | 33.4B | – | p25 | |
| ornith-ai/Ornith-1.0-9B unsloth/Ornith-1.0-9B-GGUF · Q8_0 | Fits | 57.548.9–66.2 | 256K | 9.4B | – | p20 | |
| Qwen/Qwen3-30B-A3B unsloth/Qwen3-30B-A3B-GGUF · Q4_K_S | Fits | 98.283.4–113 | 40K | 30.5B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct ggml-org/Qwen3-Coder-30B-A3B-Instruct-GGUF · Q4_K_M | Fits | 97.382.7–112 | 256K | 30.5B | – | – | |
| prism-ml/Bonsai-27B-mlx-1bit MLX-1BIT | Fits | 68.127.2–74.9 | 219K | 26.4B | – | – | |
| ornith-ai/Ornith-1.5-9B-GGUF Q8_0 | Fits | 56.247.8–64.7 | 256K | 9.2B | – | – | |
| prism-ml/Ternary-Bonsai-27B-mlx-2bit MLX-2BIT | Fits | 49.819.9–54.8 | 169K | 26.4B | – | – | |
| Qwen/Qwen3-14B unsloth/Qwen3-14B-GGUF · Q8_0 | Fits | 31.626.9–36.3 | 40K | 14.8B | – | – | |
| Qwen/Qwen2.5-14B-Instruct Qwen/Qwen2.5-14B-Instruct-GGUF · Q8_0 | Fits | 30.325.8–34.9 | 32K | 14.8B | – | – | |
| Qwen/Qwen2.5-Coder-14B-Instruct bartowski/Qwen2.5-Coder-14B-Instruct-GGUF · Q8_0 | Fits | 30.325.8–34.9 | 32K | 14.8B | – | – | |
| Qwen/Qwen2.5-32B-Instruct bartowski/Qwen2.5-32B-Instruct-GGUF · IQ3_M | Fits | 28.624.3–32.9 | 32K | 32.8B | – | – | |
| Qwen/Qwen2.5-Coder-32B-Instruct bartowski/Qwen2.5-Coder-32B-Instruct-GGUF · IQ3_M | Fits | 28.624.3–32.9 | 32K | 32.8B | – | – | |
| Qwen/Qwen3-32B unsloth/Qwen3-32B-GGUF · Q3_K_S | Fits | 28.524.2–32.8 | 40K | 32.8B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT wfakhri/OTel-2.0-LLM-31B-IT-GGUF · Q4_K_S | Fits | 27.223.1–31.3 | 34K | 31.3B | – | – | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 MIXED_PRECISION | Offload | 10642.2–158 | 1M | 47.1B | p36 | p9 | |
| ornith-ai/Ornith-1.5-35B-A3B-NVFP4 MIXED_PRECISION | Offload | 10441.7–156 | 256K | 34B | – | – | |
| nvidia/Qwen3.6-35B-A3B-NVFP4 MIXED_PRECISION | Offload | 10441.6–156 | 256K | 34B | – | – | |
| ornith-ai/Ornith-1.0-35B-GGUF Q6_K | Offload | 66.733.4–100 | 256K | 34.7B | – | – | |
| ornith-ai/Ornith-1.5-35B-A3B-GGUF Q6_K | Offload | 63.932.0–95.9 | 256K | 35.5B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 FP8 | Offload | 28.811.5–43.3 | 181K | 30.5B | – | – |
Quality = benchmark percentile against all indexed models (p50 = median). Speeds are single-user decode ranges.