| Model | Verdict | Decode tok/s | Max ctx | Size | Chat | Coding | |
|---|---|---|---|---|---|---|---|
| Qwen/Qwen3-30B-A3B-Instruct-2507 bartowski/Qwen_Qwen3-30B-A3B-Instruct-2507-GGUF · IQ2_XS | Fits | 11597.5–132 | 177K | 30.5B | p85 | – | |
| Qwen/Qwen3.5-27B bartowski/Qwen_Qwen3.5-27B-GGUF · IQ2_XXS | Fits | 44.437.8–51.1 | 33K | 27.8B | p60 | p46 | |
| Qwen/Qwen3.8-27B unsloth/Qwen3.8-27B-GGUF · UD-IQ2_S | Fits | 48.841.5–56.1 | 35K | 27.8B | p59 | p33 | |
| Qwen/Qwen3.6-27B unsloth/Qwen3.6-27B-GGUF · UD-IQ2_XXS | Fits | 45.138.4–51.9 | 38K | 27.8B | p51 | p54 | |
| Qwen/Qwen3.5-35B-A3B bartowski/Qwen_Qwen3.5-35B-A3B-GGUF · IQ1_M | Fits | 211179–242 | 256K | 36B | p49 | p35 | |
| Qwen/Qwen3.5-9B unsloth/Qwen3.5-9B-GGUF · Q8_0 | Fits | 55.647.3–64.0 | 61K | 9.7B | p46 | – | |
| ornith-ai/Ornith-1.5-9B AtomicChat/Ornith-1.5-9B-GGUF · Q8_0 | Fits | 55.647.3–64.0 | 61K | 9.7B | p46 | p24 | |
| ornith-ai/Ornith-1.0-35B bartowski/deepreinforce-ai_Ornith-1.0-35B-GGUF · IQ2_XXS | Fits | 208177–240 | 256K | 35.1B | – | p40 | |
| Qwen/Qwen3.5-4B unsloth/Qwen3.5-4B-GGUF · Q8_0 | Fits | 91.577.8–105 | 175K | 4.7B | p39 | – | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · Q6_K | Fits | 46.439.4–53.4 | 51K | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 unsloth/Qwen3-4B-Instruct-2507-GGUF · Q8_0 | Fits | 75.464.1–86.7 | 42K | 4B | p38 | – | |
| poolside/Laguna-XS-2.1 bartowski/Laguna-XS-2.1-GGUF · IQ2_XXS | Fits | 200170–230 | 256K | 33.4B | – | p30 | |
| poolside/Laguna-XS.2 poolside-laguna-hackathon/Piscina-XS.2-GGUF · IQ1 | Fits | 204174–235 | 231K | 33.4B | – | p25 | |
| ornith-ai/Ornith-1.0-9B unsloth/Ornith-1.0-9B-GGUF · Q8_0 | Fits | 55.747.4–64.1 | 61K | 9.4B | – | p20 | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF · UD-TQ1_0 | Fits | 11698.7–134 | 177K | 30.5B | – | – | |
| prism-ml/Bonsai-27B-mlx-1bit MLX-1BIT | Fits | 66.826.7–73.4 | 77K | 26.4B | – | – | |
| ornith-ai/Ornith-1.5-9B-GGUF Q8_0 | Fits | 54.546.3–62.6 | 53K | 9.2B | – | – | |
| Qwen/Qwen3-14B unsloth/Qwen3-14B-GGUF · Q3_K_M | Fits | 53.145.1–61.0 | 39K | 14.8B | – | – | |
| Qwen/Qwen2.5-Coder-14B-Instruct Qwen/Qwen2.5-Coder-14B-Instruct-GGUF · Q3_K_M | Fits | 49.542.0–56.9 | 32K | 14.8B | – | – | |
| Qwen/Qwen2.5-14B-Instruct Qwen/Qwen2.5-14B-Instruct-GGUF · Q3_K_M | Fits | 49.542.0–56.9 | 32K | 14.8B | – | – | |
| prism-ml/Ternary-Bonsai-27B-mlx-2bit MLX-2BIT | Tight fit | 48.619.5–53.5 | 28K | 26.4B | – | – | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · IQ4_XS | Offload | 3.001.50–4.50 | 0 | 31.3B | p63 | – | |
| google/gemma-4-26B-A4B-it unsloth/gemma-4-26B-A4B-it-GGUF · Q8_0 | Offload | 26.713.3–40.0 | 256K | 25.8B | p49 | – | |
| Qwen/Qwen3.6-35B-A3B unsloth/Qwen3.6-35B-A3B-MTP-GGUF · Q8_0 | Offload | 34.017.0–51.0 | 256K | 36B | p43 | p41 | |
| openbmb/MiniCPM-V-4.7-35B-A3B openbmb/MiniCPM-V-4.7-35B-A3B-gguf · Q8_0 | Offload | 34.717.4–52.1 | 256K | 35.2B | p42 | – | |
| openai/gpt-oss-20b unsloth/gpt-oss-20b-GGUF · F16 | Offload | 56.128.0–84.1 | 128K | 21.1B | p39 | p15 | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF · Q8_0 | Offload | 27.713.9–41.6 | 256K | 32.9B | p37 | p9 | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 MIXED_PRECISION | Offload | 48.419.3–72.5 | 1M | 47.1B | p36 | p9 | |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 unsloth/Nemotron-3-Nano-30B-A3B-GGUF · Q6_K | Offload | 27.813.9–41.7 | 256K | 31.6B | p33 | – | |
| ornith-ai/Ornith-1.5-35B-A3B-NVFP4 MIXED_PRECISION | Offload | 58.723.5–88.0 | 256K | 34B | – | – | |
| nvidia/Qwen3.6-35B-A3B-NVFP4 MIXED_PRECISION | Offload | 58.723.5–88.0 | 256K | 34B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 FP8 | Offload | 20.28.10–30.3 | 86K | 30.5B | – | – | |
| Qwen/Qwen3-30B-A3B unsloth/Qwen3-30B-A3B-GGUF · Q8_0 | Offload | 19.59.80–29.3 | 40K | 30.5B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT wfakhri/OTel-2.0-LLM-31B-IT-GGUF · Q3_K_M | Offload | 3.301.70–5.00 | 0 | 31.3B | – | – | |
| Qwen/Qwen3-32B unsloth/Qwen3-32B-GGUF · Q2_K | Offload | 3.001.50–4.50 | 0 | 32.8B | – | – | |
| Qwen/Qwen2.5-32B-Instruct Qwen/Qwen2.5-32B-Instruct-GGUF · Q2_K | Offload | 3.001.50–4.50 | 0 | 32.8B | – | – | |
| Qwen/Qwen2.5-Coder-32B-Instruct bartowski/Qwen2.5-Coder-32B-Instruct-GGUF · Q2_K | Offload | 3.001.50–4.50 | 0 | 32.8B | – | – |
Quality = benchmark percentile against all indexed models (p50 = median). Speeds are single-user decode ranges.