| Model | Verdict | Decode tok/s | Max ctx | Size | Chat | Coding | |
|---|---|---|---|---|---|---|---|
| Qwen/Qwen3-30B-A3B-Instruct-2507 BF16 | Fits | 13052.2–143 | 256K | 30.5B | p85 | – | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · Q8_0 | Fits | 46.539.5–53.5 | 256K | 31.3B | p63 | – | |
| Qwen/Qwen3.5-27B unsloth/Qwen3.5-27B-GGUF · Q8_0 | Fits | 50.442.8–57.9 | 256K | 27.8B | p60 | p46 | |
| Qwen/Qwen3.8-27B unsloth/Qwen3.8-27B-GGUF · Q8_0 | Fits | 49.842.3–57.2 | 256K | 27.8B | p59 | p33 | |
| Qwen/Qwen3.6-27B unsloth/Qwen3.6-27B-GGUF · Q8_0 | Fits | 50.442.8–57.9 | 256K | 27.8B | p51 | p54 | |
| Qwen/Qwen3.5-35B-A3B BF16 | Fits | 13353.3–147 | 256K | 36B | p49 | p35 | |
| google/gemma-4-26B-A4B-it BF16 | Fits | 13955.5–153 | 256K | 25.8B | p49 | – | |
| Qwen/Qwen3.5-9B BF16 | Fits | 84.033.6–92.4 | 256K | 9.7B | p46 | – | |
| ornith-ai/Ornith-1.5-9B BF16 | Fits | 84.033.6–92.4 | 256K | 9.7B | p46 | p24 | |
| Qwen/Qwen3.6-35B-A3B BF16 | Fits | 13353.3–147 | 256K | 36B | p43 | p41 | |
| openbmb/MiniCPM-V-4.7-35B-A3B BF16 | Fits | 15059.8–164 | 256K | 35.2B | p42 | – | |
| ornith-ai/Ornith-1.0-35B BF16 | Fits | 15260.9–167 | 256K | 35.1B | – | p40 | |
| openai/gpt-oss-20b MXFP4 | Fits | 22489.6–246 | 128K | 21.1B | p39 | p15 | |
| Qwen/Qwen3.5-4B BF16 | Fits | 13453.5–147 | 256K | 4.7B | p39 | – | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · Q8_0 | Fits | 10690.0–122 | 256K | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 BF16 | Fits | 14256.9–156 | 256K | 4B | p38 | – | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF · BF16 | Fits | 146124–168 | 256K | 32.9B | p37 | p9 | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 MIXED_PRECISION | Fits | 22288.8–244 | 1M | 47.1B | p36 | p9 | |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 unsloth/Nemotron-3-Nano-30B-A3B-GGUF · BF16 | Fits | 150127–172 | 256K | 31.6B | p33 | – | |
| poolside/Laguna-XS-2.1 BF16 | Fits | 16666.4–183 | 256K | 33.4B | – | p30 | |
| poolside/Laguna-XS.2 BF16 | Fits | 16666.4–183 | 256K | 33.4B | – | p25 | |
| ornith-ai/Ornith-1.0-9B BF16 | Fits | 86.034.4–94.6 | 256K | 9.4B | – | p20 | |
| ornith-ai/Ornith-1.5-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 271108–298 | 256K | 34B | – | – | |
| nvidia/Qwen3.6-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 271108–298 | 256K | 34B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 FP8 | Fits | 16666.5–183 | 256K | 30.5B | – | – | |
| prism-ml/Bonsai-27B-mlx-1bit MLX-1BIT | Fits | 13554.0–149 | 256K | 26.4B | – | – | |
| Qwen/Qwen3-30B-A3B BF16 | Fits | 13052.2–143 | 40K | 30.5B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct BF16 | Fits | 13052.2–143 | 256K | 30.5B | – | – | |
| prism-ml/Ternary-Bonsai-27B-mlx-2bit MLX-2BIT | Fits | 10943.6–120 | 256K | 26.4B | – | – | |
| Qwen/Qwen3-14B unsloth/Qwen3-14B-GGUF · Q8_0 | Fits | 89.676.1–103 | 40K | 14.8B | – | – | |
| ornith-ai/Ornith-1.5-9B-GGUF BF16 | Fits | 87.274.2–100 | 256K | 9.2B | – | – | |
| Qwen/Qwen2.5-14B-Instruct Qwen/Qwen2.5-14B-Instruct-GGUF · Q8_0 | Fits | 85.172.4–97.9 | 32K | 14.8B | – | – | |
| Qwen/Qwen2.5-Coder-14B-Instruct Qwen/Qwen2.5-Coder-14B-Instruct-GGUF · Q4_K_M | Fits | 77.365.7–88.9 | 32K | 14.8B | – | – | |
| RadixArk/Qwen3.8-27B-NVFP4 MIXED_PRECISION | Fits | 61.424.6–67.5 | 256K | 26.4B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT wfakhri/OTel-2.0-LLM-31B-IT-GGUF · Q8_0 | Fits | 46.539.5–53.5 | 256K | 31.3B | – | – | |
| Qwen/Qwen2.5-32B-Instruct Qwen/Qwen2.5-32B-Instruct-GGUF · Q8_0 | Fits | 42.536.1–48.9 | 32K | 32.8B | – | – | |
| Qwen/Qwen3-32B unsloth/Qwen3-32B-GGUF · Q8_0 | Fits | 42.035.7–48.4 | 40K | 32.8B | – | – | |
| Qwen/Qwen2.5-Coder-32B-Instruct Qwen/Qwen2.5-Coder-32B-Instruct-GGUF · Q4_K_M | Fits | 38.232.5–43.9 | 32K | 32.8B | – | – |
Quality = benchmark percentile against all indexed models (p50 = median). Speeds are single-user decode ranges.