| Model | Verdict | Decode tok/s | Max ctx | Size | Chat | Coding | |
|---|---|---|---|---|---|---|---|
| Qwen/Qwen3.6-27B prism-ml/Bonsai-27B-gguf · Q1_0 | Fits | 47.419.0–52.1 | 37K | 27.8B | p51 | p54 | |
| Qwen/Qwen3.5-9B unsloth/Qwen3.5-9B-GGUF · Q3_K_M | Fits | 56.347.8–64.7 | 44K | 9.7B | p46 | – | |
| ornith-ai/Ornith-1.5-9B bartowski/Ornith-1.5-9B-GGUF · Q3_K_M | Fits | 54.146.0–62.2 | 33K | 9.7B | p46 | p24 | |
| Qwen/Qwen3.5-4B unsloth/Qwen3.5-4B-GGUF · Q8_0 | Fits | 53.445.4–61.4 | 34K | 4.7B | p39 | – | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · UD-IQ2_M | Fits | 44.337.7–51.0 | 68K | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 unsloth/Qwen3-4B-Instruct-2507-GGUF · Q4_K_M | Fits | 53.945.8–62.0 | 33K | 4B | p38 | – | |
| ornith-ai/Ornith-1.0-9B unsloth/Ornith-1.0-9B-GGUF · Q3_K_M | Fits | 56.247.7–64.6 | 43K | 9.4B | – | p20 | |
| Qwen/Qwen3-30B-A3B-Instruct-2507 unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF · BF16 | Offload | 14.37.20–21.5 | 0 | 30.5B | p85 | – | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · UD-IQ2_M | Offload | 3.001.50–4.50 | 0 | 31.3B | p63 | – | |
| Qwen/Qwen3.5-27B unsloth/Qwen3.5-27B-GGUF · Q3_K_S | Offload | 3.001.50–4.60 | 0 | 27.8B | p60 | p46 | |
| Qwen/Qwen3.8-27B unsloth/Qwen3.8-27B-GGUF · UD-IQ3_S | Offload | 3.101.50–4.60 | 0 | 27.8B | p59 | p33 | |
| Qwen/Qwen3.5-35B-A3B bartowski/Qwen_Qwen3.5-35B-A3B-GGUF · Q2_K_L | Offload | 66.233.1–99.3 | 81K | 36B | p49 | p35 | |
| google/gemma-4-26B-A4B-it unsloth/gemma-4-26B-A4B-it-GGUF · UD-IQ4_NL | Offload | 41.420.7–62.1 | 82K | 25.8B | p49 | – | |
| Qwen/Qwen3.6-35B-A3B unsloth/Qwen3.6-35B-A3B-MTP-GGUF · UD-IQ3_XXS | Offload | 66.033.0–99.0 | 79K | 36B | p43 | p41 | |
| openbmb/MiniCPM-V-4.7-35B-A3B openbmb/MiniCPM-V-4.7-35B-A3B-gguf · IQ3_XS | Offload | 64.832.4–97.2 | 61K | 35.2B | p42 | – | |
| ornith-ai/Ornith-1.0-35B bartowski/deepreinforce-ai_Ornith-1.0-35B-GGUF · IQ3_XXS | Offload | 64.532.3–96.8 | 72K | 35.1B | – | p40 | |
| openai/gpt-oss-20b unsloth/gpt-oss-20b-GGUF · F16 | Offload | 28.314.1–42.4 | 116K | 21.1B | p39 | p15 | |
| poolside/Laguna-XS-2.1 bartowski/Laguna-XS-2.1-GGUF · IQ3_XXS | Offload | 65.032.5–97.5 | 54K | 33.4B | – | p30 | |
| poolside/Laguna-XS.2 poolside-laguna-hackathon/Piscina-XS.2-GGUF · IQ2 | Offload | 73.036.5–110 | 87K | 33.4B | – | p25 | |
| Qwen/Qwen3-30B-A3B unsloth/Qwen3-30B-A3B-GGUF · BF16 | Offload | 14.37.20–21.5 | 0 | 30.5B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF · BF16 | Offload | 14.37.20–21.5 | 0 | 30.5B | – | – | |
| ornith-ai/Ornith-1.5-9B-GGUF Q8_0 | Offload | 4.402.20–6.60 | 0 | 9.2B | – | – | |
| Qwen/Qwen3-14B unsloth/Qwen3-14B-GGUF · Q5_K_M | Offload | 3.401.70–5.20 | 0 | 14.8B | – | – | |
| Qwen/Qwen3-32B unsloth/Qwen3-32B-GGUF · UD-IQ2_XXS | Offload | 3.301.60–4.90 | 0 | 32.8B | – | – | |
| Qwen/Qwen2.5-14B-Instruct Qwen/Qwen2.5-14B-Instruct-GGUF · Q5_K_M | Offload | 3.201.60–4.90 | 0 | 14.8B | – | – | |
| Qwen/Qwen2.5-Coder-14B-Instruct bartowski/Qwen2.5-Coder-14B-Instruct-GGUF · Q5_K_L | Offload | 3.101.50–4.60 | 0 | 14.8B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT wfakhri/OTel-2.0-LLM-31B-IT-GGUF · IQ2_M | Offload | 3.001.50–4.50 | 0 | 31.3B | – | – | |
| Qwen/Qwen2.5-Coder-32B-Instruct bartowski/Qwen2.5-Coder-32B-Instruct-GGUF · IQ2_S | Offload | 3.001.50–4.50 | 0 | 32.8B | – | – | |
| Qwen/Qwen2.5-32B-Instruct bartowski/Qwen2.5-32B-Instruct-GGUF · IQ2_S | Offload | 3.001.50–4.50 | 0 | 32.8B | – | – |
Quality = benchmark percentile against all indexed models (p50 = median). Speeds are single-user decode ranges.