| Model | Verdict | Decode tok/s | Max ctx | Size | Chat | Coding | |
|---|---|---|---|---|---|---|---|
| Qwen/Qwen3.5-9B prism-ml/Ternary-Bonsai-2-9B-gguf · Q2_0 | Fits | 52.244.4–60.0 | 36K | 9.7B | p46 | – | |
| Qwen/Qwen3.5-4B unsloth/Qwen3.5-4B-GGUF · Q3_K_M | Fits | 52.144.3–59.9 | 35K | 4.7B | p39 | – | |
| Qwen/Qwen3-30B-A3B-Instruct-2507 unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF · Q8_0 | Offload | 20.010.0–30.0 | 0 | 30.5B | p85 | – | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · UD-IQ2_XXS | Offload | 3.301.70–5.00 | 0 | 31.3B | p63 | – | |
| Qwen/Qwen3.5-27B bartowski/Qwen_Qwen3.5-27B-GGUF · IQ2_XXS | Offload | 3.001.50–4.50 | 0 | 27.8B | p60 | p46 | |
| Qwen/Qwen3.8-27B unsloth/Qwen3.8-27B-GGUF · UD-IQ2_S | Offload | 3.501.70–5.20 | 0 | 27.8B | p59 | p33 | |
| Qwen/Qwen3.6-27B unsloth/Qwen3.6-27B-GGUF · UD-IQ2_XXS | Offload | 3.101.60–4.70 | 0 | 27.8B | p51 | p54 | |
| Qwen/Qwen3.5-35B-A3B unsloth/Qwen3.5-35B-A3B-GGUF · BF16 | Offload | 9.804.90–14.8 | 0 | 36B | p49 | p35 | |
| google/gemma-4-26B-A4B-it unsloth/gemma-4-26B-A4B-it-GGUF · Q8_0 | Offload | 23.011.5–34.4 | 0 | 25.8B | p49 | – | |
| ornith-ai/Ornith-1.5-9B AtomicChat/Ornith-1.5-9B-GGUF · Q8_0 | Offload | 3.301.70–5.00 | 0 | 9.7B | p46 | p24 | |
| Qwen/Qwen3.6-35B-A3B unsloth/Qwen3.6-35B-A3B-GGUF · BF16 | Offload | 9.804.90–14.8 | 0 | 36B | p43 | p41 | |
| openbmb/MiniCPM-V-4.7-35B-A3B openbmb/MiniCPM-V-4.7-35B-A3B-gguf · F16 | Offload | 9.904.90–14.8 | 0 | 35.2B | p42 | – | |
| ornith-ai/Ornith-1.0-35B unsloth/Ornith-1.0-35B-GGUF · BF16 | Offload | 9.904.90–14.8 | 0 | 35.1B | – | p40 | |
| openai/gpt-oss-20b unsloth/gpt-oss-20b-GGUF · Q8_0 | Offload | 26.513.3–39.8 | 78K | 21.1B | p39 | p15 | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · Q6_K | Offload | 3.201.60–4.80 | 0 | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 unsloth/Qwen3-4B-Instruct-2507-GGUF · F16 | Offload | 3.301.60–4.90 | 0 | 4B | p38 | – | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF · BF16 | Offload | 11.45.70–17.1 | 0 | 32.9B | p37 | p9 | |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 unsloth/Nemotron-3-Nano-30B-A3B-GGUF · BF16 | Offload | 11.45.70–17.1 | 0 | 31.6B | p33 | – | |
| poolside/Laguna-XS-2.1 poolside/Laguna-XS-2.1-GGUF · BF16 | Offload | 14.67.30–21.8 | 0 | 33.4B | – | p30 | |
| poolside/Laguna-XS.2 poolside-laguna-hackathon/Laguna-XS.2-GGUF · Q4_K_M | Offload | 17.58.80–26.3 | 0 | 33.4B | – | p25 | |
| ornith-ai/Ornith-1.0-9B unsloth/Ornith-1.0-9B-GGUF · Q8_0 | Offload | 3.301.70–5.00 | 0 | 9.4B | – | p20 | |
| Qwen/Qwen3-30B-A3B unsloth/Qwen3-30B-A3B-GGUF · Q8_0 | Offload | 20.010.0–30.0 | 0 | 30.5B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF · Q8_0 | Offload | 20.010.0–30.0 | 0 | 30.5B | – | – | |
| Qwen/Qwen3-14B unsloth/Qwen3-14B-GGUF · UD-IQ2_M | Offload | 4.902.40–7.30 | 0 | 14.8B | – | – | |
| ornith-ai/Ornith-1.5-9B-GGUF Q8_0 | Offload | 3.301.60–4.90 | 0 | 9.2B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT wfakhri/OTel-2.0-LLM-31B-IT-GGUF · IQ3_XS | Offload | 2.201.10–3.30 | 0 | 31.3B | – | – |
Quality = benchmark percentile against all indexed models (p50 = median). Speeds are single-user decode ranges.