| Model | Verdict | Decode tok/s | Max ctx | Size | Chat | Coding | |
|---|---|---|---|---|---|---|---|
| Qwen/Qwen3-30B-A3B-Instruct-2507 BF16 | Fits | 52.821.1–58.0 | 256K | 30.5B | p85 | – | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · Q8_0 | Fits | 15.112.9–17.4 | 256K | 31.3B | p63 | – | |
| Qwen/Qwen3.5-27B unsloth/Qwen3.5-27B-GGUF · Q8_0 | Fits | 17.915.2–20.6 | 256K | 27.8B | p60 | p46 | |
| Qwen/Qwen3.8-27B unsloth/Qwen3.8-27B-GGUF · Q8_0 | Fits | 17.715.0–20.3 | 256K | 27.8B | p59 | p33 | |
| Qwen/Qwen3.6-27B unsloth/Qwen3.6-27B-GGUF · Q8_0 | Fits | 17.915.2–20.6 | 256K | 27.8B | p51 | p54 | |
| Qwen/Qwen3.5-35B-A3B unsloth/Qwen3.5-35B-A3B-GGUF · BF16 | Fits | 79.567.6–91.5 | 256K | 36B | p49 | p35 | |
| google/gemma-4-26B-A4B-it unsloth/gemma-4-26B-A4B-it-GGUF · Q8_0 | Fits | 10185.8–116 | 256K | 25.8B | p49 | – | |
| Qwen/Qwen3.5-9B unsloth/Qwen3.5-9B-GGUF · Q8_0 | Fits | 53.945.9–62.0 | 256K | 9.7B | p46 | – | |
| ornith-ai/Ornith-1.5-9B AtomicChat/Ornith-1.5-9B-GGUF · Q8_0 | Fits | 53.945.9–62.0 | 256K | 9.7B | p46 | p24 | |
| Qwen/Qwen3.6-35B-A3B unsloth/Qwen3.6-35B-A3B-GGUF · BF16 | Fits | 79.567.6–91.5 | 256K | 36B | p43 | p41 | |
| openbmb/MiniCPM-V-4.7-35B-A3B openbmb/MiniCPM-V-4.7-35B-A3B-gguf · F16 | Fits | 79.867.8–91.7 | 256K | 35.2B | p42 | – | |
| ornith-ai/Ornith-1.0-35B unsloth/Ornith-1.0-35B-GGUF · BF16 | Fits | 79.867.8–91.8 | 256K | 35.1B | – | p40 | |
| openai/gpt-oss-20b MXFP4 | Fits | 88.735.5–97.6 | 128K | 21.1B | p39 | p15 | |
| Qwen/Qwen3.5-4B unsloth/Qwen3.5-4B-GGUF · Q8_0 | Fits | 88.575.2–102 | 256K | 4.7B | p39 | – | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · Q8_0 | Fits | 35.430.1–40.7 | 256K | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 unsloth/Qwen3-4B-Instruct-2507-GGUF · Q8_0 | Fits | 72.061.2–82.8 | 256K | 4B | p38 | – | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF · Q8_0 | Fits | 10185.5–116 | 256K | 32.9B | p37 | p9 | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 MIXED_PRECISION | Fits | 12951.7–142 | 1M | 47.1B | p36 | p9 | |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 unsloth/Nemotron-3-Nano-30B-A3B-GGUF · Q8_0 | Fits | 10387.9–119 | 256K | 31.6B | p33 | – | |
| poolside/Laguna-XS-2.1 poolside/Laguna-XS-2.1-GGUF · BF16 | Fits | 85.872.9–98.7 | 256K | 33.4B | – | p30 | |
| poolside/Laguna-XS.2 BF16 | Fits | 70.528.2–77.6 | 256K | 33.4B | – | p25 | |
| ornith-ai/Ornith-1.0-9B unsloth/Ornith-1.0-9B-GGUF · Q8_0 | Fits | 54.146.0–62.2 | 256K | 9.4B | – | p20 | |
| ornith-ai/Ornith-1.5-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 14658.6–161 | 256K | 34B | – | – | |
| nvidia/Qwen3.6-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 14658.6–161 | 256K | 34B | – | – | |
| ornith-ai/Ornith-1.0-35B-GGUF Q8_0 | Fits | 10387.6–119 | 256K | 34.7B | – | – | |
| ornith-ai/Ornith-1.5-35B-A3B-GGUF Q8_0 | Fits | 10186.0–116 | 256K | 35.5B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 FP8 | Fits | 73.429.4–80.7 | 256K | 30.5B | – | – | |
| prism-ml/Bonsai-27B-mlx-1bit MLX-1BIT | Fits | 63.925.5–70.3 | 256K | 26.4B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct BF16 | Fits | 52.821.1–58.0 | 256K | 30.5B | – | – | |
| Qwen/Qwen3-30B-A3B BF16 | Fits | 52.821.1–58.0 | 40K | 30.5B | – | – | |
| ornith-ai/Ornith-1.5-9B-GGUF Q8_0 | Fits | 52.844.9–60.8 | 256K | 9.2B | – | – | |
| prism-ml/Ternary-Bonsai-27B-mlx-2bit MLX-2BIT | Fits | 46.718.7–51.4 | 256K | 26.4B | – | – | |
| Qwen/Qwen3-14B unsloth/Qwen3-14B-GGUF · Q8_0 | Fits | 29.625.2–34.0 | 40K | 14.8B | – | – | |
| Qwen/Qwen2.5-14B-Instruct Qwen/Qwen2.5-14B-Instruct-GGUF · Q8_0 | Fits | 28.424.1–32.6 | 32K | 14.8B | – | – | |
| Qwen/Qwen2.5-Coder-14B-Instruct Qwen/Qwen2.5-Coder-14B-Instruct-GGUF · Q4_K_M | Fits | 25.621.7–29.4 | 32K | 14.8B | – | – | |
| RadixArk/Qwen3.8-27B-NVFP4 MIXED_PRECISION | Fits | 22.69.00–24.8 | 256K | 26.4B | – | – | |
| Qwen/Qwen2.5-Coder-32B-Instruct Qwen/Qwen2.5-Coder-32B-Instruct-GGUF · Q3_K_M | Fits | 14.912.7–17.1 | 32K | 32.8B | – | – | |
| Qwen/Qwen2.5-32B-Instruct Qwen/Qwen2.5-32B-Instruct-GGUF · Q8_0 | Fits | 13.811.7–15.9 | 32K | 32.8B | – | – | |
| Qwen/Qwen3-32B unsloth/Qwen3-32B-GGUF · Q8_0 | Fits | 13.611.6–15.6 | 40K | 32.8B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT BF16 | Fits | 4.301.70–4.70 | 256K | 31.3B | – | – |
Quality = benchmark percentile against all indexed models (p50 = median). Speeds are single-user decode ranges.