| Model | Verdict | Decode tok/s | Max ctx | Size | Chat | Coding | |
|---|---|---|---|---|---|---|---|
| Qwen/Qwen3-30B-A3B-Instruct-2507 unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF · Q5_K_M | Fits | 143108–179 | 256K | 30.5B | p85 | – | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · Q5_K_M | Fits | 23.320.9–25.6 | 41K | 31.3B | p63 | – | |
| Qwen/Qwen3.5-27B unsloth/Qwen3.5-27B-GGUF · Q6_K | Fits | 27.925.1–30.7 | 42K | 27.8B | p60 | p46 | |
| Qwen/Qwen3.8-27B unsloth/Qwen3.8-27B-GGUF · Q4_1 | Fits | 35.130.2–40.1 | 111K | 27.8B | p59 | p33 | |
| Qwen/Qwen3.6-27B unsloth/Qwen3.6-27B-GGUF · Q6_K | Fits | 27.825.1–30.6 | 41K | 27.8B | p51 | p54 | |
| Qwen/Qwen3.5-35B-A3B unsloth/Qwen3.5-35B-A3B-GGUF · Q4_K_M | Fits | 297223–372 | 256K | 36B | p49 | p35 | |
| google/gemma-4-26B-A4B-it unsloth/gemma-4-26B-A4B-it-GGUF · MXFP4_MOE | Fits | 12392.2–154 | 256K | 25.8B | p49 | – | |
| Qwen/Qwen3.5-9B unsloth/Qwen3.5-9B-GGUF · Q8_0 | Fits | 69.659.8–79.3 | 256K | 9.7B | p46 | – | |
| ornith-ai/Ornith-1.5-9B BF16 | Fits | 44.317.7–48.7 | 149K | 9.7B | p46 | p24 | |
| Qwen/Qwen3.6-35B-A3B unsloth/Qwen3.6-35B-A3B-MTP-GGUF · MXFP4_MOE | Fits | 296222–370 | 256K | 36B | p43 | p41 | |
| openbmb/MiniCPM-V-4.7-35B-A3B openbmb/MiniCPM-V-4.7-35B-A3B-gguf · Q5_K_S | Fits | 279210–349 | 256K | 35.2B | p42 | – | |
| ornith-ai/Ornith-1.0-35B bartowski/deepreinforce-ai_Ornith-1.0-35B-GGUF · Q4_K_L | Fits | 301226–376 | 256K | 35.1B | – | p40 | |
| openai/gpt-oss-20b unsloth/gpt-oss-20b-GGUF · F16 | Fits | 217163–271 | 128K | 21.1B | p39 | p15 | |
| Qwen/Qwen3.5-4B BF16 | Fits | 74.529.8–81.9 | 256K | 4.7B | p39 | – | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · Q8_0 | Fits | 44.138.0–50.3 | 256K | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 BF16 | Fits | 74.329.7–81.7 | 108K | 4B | p38 | – | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 bartowski/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF · Q4_K_S | Fits | 254191–318 | 256K | 32.9B | p37 | p9 | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 MIXED_PRECISION | Fits | 16766.7–184 | 1M | 47.1B | p36 | p9 | |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 unsloth/Nemotron-3-Nano-30B-A3B-GGUF · Q5_K_S | Fits | 248186–310 | 256K | 31.6B | p33 | – | |
| poolside/Laguna-XS-2.1 poolside/Laguna-XS-2.1-GGUF · Q4_K_M | Fits | 302226–377 | 256K | 33.4B | – | p30 | |
| Qwen/Qwen2.5-7B BF16 | Fits | 53.521.4–58.8 | 128K | 7.6B | p29 | – | |
| google/gemma-4-E4B-it BF16 | Fits | 71.328.5–78.4 | 128K | 8B | p27 | – | |
| openbmb/MiniCPM5-2B BF16 | Fits | 12349.0–135 | 128K | 2.5B | p27 | p3 | |
| poolside/Laguna-XS.2 Lucebox/Laguna-XS.2-GGUF · Q4_K_M | Fits | 302226–377 | 256K | 33.4B | – | p25 | |
| Qwen/Qwen3.5-2B BF16 | Fits | 14256.8–156 | 256K | 2.3B | p24 | – | |
| ornith-ai/Ornith-1.0-9B unsloth/Ornith-1.0-9B-GGUF · Q8_0 | Fits | 69.760.0–79.5 | 256K | 9.4B | – | p20 | |
| google/gemma-4-E2B-it BF16 | Fits | 12047.9–132 | 128K | 5.1B | p18 | – | |
| Qwen/Qwen2.5-1.5B BF16 | Fits | 18674.4–205 | 128K | 1.5B | p15 | – | |
| mistralai/Mistral-7B-Instruct-v0.2 BF16 | Fits | 49.819.9–54.7 | 32K | 7.2B | p14 | – | |
| Qwen/Qwen2.5-0.5B BF16 | Fits | 435174–479 | 32K | 0.5B | p5 | – | |
| Qwen/Qwen3.5-0.8B BF16 | Fits | 262105–288 | 256K | 0.9B | p4 | – | |
| incoai/Qwen3.8-27B-DFlash2 BF16 | Fits | 589236–648 | 256K | 1.9B | – | – | |
| Qwen/Qwen2.5-0.5B-Instruct BF16 | Fits | 435174–479 | 32K | 0.5B | – | – | |
| datalab-to/surya-ocr-2 BF16 | Fits | 295118–325 | 256K | 0.7B | – | – | |
| baidu/Unlimited-OCR-2 AtomicChat/Unlimited-OCR-2-GGUF · BF16 | Fits | 290217–362 | 128K | 3.3B | – | – | |
| Qwen/Qwen3.5-0.8B-Base BF16 | Fits | 262105–288 | 256K | 0.9B | – | – | |
| ornith-ai/Ornith-1.0-35B-GGUF Q4_K_M | Fits | 247186–309 | 256K | 34.7B | – | – | |
| ornith-ai/Ornith-1.5-35B-A3B-GGUF Q4_K_M | Fits | 244183–305 | 256K | 35.5B | – | – | |
| Qwen/Qwen3-0.6B-Base BF16 | Fits | 22389.1–245 | 32K | 0.6B | – | – | |
| openbmb/MiniCPM-V-4.7-1B BF16 | Fits | 20883.3–229 | 256K | 1.6B | – | – | |
| Qwen/Qwen3-0.6B BF16 | Fits | 20682.5–227 | 40K | 0.8B | – | – | |
| nvidia/Qwen3.6-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 19678.4–216 | 256K | 34B | – | – | |
| ornith-ai/Ornith-1.5-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 19678.4–216 | 256K | 34B | – | – | |
| Qwen/Qwen2.5-1.5B-Instruct BF16 | Fits | 18674.4–205 | 32K | 1.5B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 ijohn07/Qwen3-Coder-30B-A3B-Instruct-FP8-Q4_K_M-GGUF · Q4_K_M | Fits | 156117–195 | 231K | 30.5B | – | – | |
| Qwen/Qwen2-VL-2B-Instruct BF16 | Fits | 14557.9–159 | 32K | 2.2B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF · Q5_K_M | Fits | 143108–179 | 256K | 30.5B | – | – | |
| Qwen/Qwen3-30B-A3B unsloth/Qwen3-30B-A3B-GGUF · Q5_K_M | Fits | 143108–179 | 40K | 30.5B | – | – | |
| Qwen/Qwen3-1.7B-Base BF16 | Fits | 14156.5–156 | 32K | 1.7B | – | – | |
| baidu/Unlimited-OCR BF16 | Fits | 14055.9–154 | 32K | 3.3B | – | – | |
| Qwen/Qwen3-1.7B BF16 | Fits | 12851.4–141 | 40K | 2B | – | – | |
| Qwen/Qwen3-VL-2B-Instruct BF16 | Fits | 12549.9–137 | 171K | 2.1B | – | – | |
| openbmb/MiniCPM5-2B-GGUF F16 | Fits | 10892.7–123 | 128K | 2.5B | – | – | |
| Qwen/Qwen2.5-3B-Instruct BF16 | Fits | 10441.4–114 | 32K | 3.1B | – | – | |
| Qwen/Qwen2.5-VL-3B-Instruct BF16 | Fits | 89.335.7–98.3 | 125K | 3.8B | – | – | |
| prism-ml/Bonsai-27B-mlx-1bit MLX-1BIT | Fits | 88.935.6–97.8 | 256K | 26.4B | – | – | |
| nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF · BF16 | Fits | 86.874.6–98.9 | 256K | 4B | – | – | |
| ornith-ai/Ornith-1.5-9B-NVFP4 MIXED_PRECISION | Fits | 85.434.2–93.9 | 256K | 9B | – | – | |
| Qwen/Qwen3.5-4B-Base BF16 | Fits | 74.529.8–81.9 | 256K | 4.7B | – | – | |
| Qwen/Qwen3-4B BF16 | Fits | 74.329.7–81.7 | 40K | 4B | – | – | |
| Qwen/Qwen2.5-7B-Instruct Qwen/Qwen2.5-7B-Instruct-GGUF · Q8_0 | Fits | 71.361.3–81.2 | 32K | 7.6B | – | – | |
| ornith-ai/Ornith-1.0-9B-GGUF Q8_0 | Fits | 70.160.3–80.0 | 256K | 9B | – | – | |
| Qwen/Qwen3-VL-4B-Instruct BF16 | Fits | 69.327.7–76.3 | 103K | 4.4B | – | – | |
| ornith-ai/Ornith-1.5-9B-GGUF Q8_0 | Fits | 68.258.7–77.8 | 256K | 9.2B | – | – | |
| datalab-to/chandra-ocr-2 BF16 | Fits | 67.226.9–73.9 | 256K | 5.3B | – | – | |
| prism-ml/Ternary-Bonsai-27B-mlx-2bit MLX-2BIT | Fits | 67.026.8–73.7 | 232K | 26.4B | – | – | |
| HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive Q8_K_P | Fits | 64.055.0–73.0 | 128K | 7.5B | – | – | |
| Qwen/Qwen2.5-Coder-7B-Instruct Qwen/Qwen2.5-Coder-7B-Instruct-GGUF · Q4_K_M | Fits | 62.956.6–69.2 | 32K | 7.6B | – | – | |
| Qwen/Qwen2.5-VL-7B-Instruct BF16 | Fits | 49.419.8–54.3 | 125K | 8.3B | – | – | |
| Qwen/Qwen2-VL-7B-Instruct BF16 | Fits | 49.419.8–54.3 | 32K | 8.3B | – | – | |
| Qwen/Qwen3-8B BF16 | Fits | 46.318.5–50.9 | 40K | 8.2B | – | – | |
| Qwen/Qwen3-8B-Base BF16 | Fits | 46.318.5–50.9 | 32K | 8.2B | – | – | |
| Qwen/Qwen3-VL-8B-Instruct BF16 | Fits | 43.617.4–48.0 | 46K | 8.8B | – | – | |
| Qwen/Qwen3-14B unsloth/Qwen3-14B-GGUF · Q8_0 | Fits | 35.130.2–40.0 | 40K | 14.8B | – | – | |
| Qwen/Qwen2.5-14B-Instruct Qwen/Qwen2.5-14B-Instruct-GGUF · Q8_0 | Fits | 33.929.2–38.6 | 32K | 14.8B | – | – | |
| RadixArk/Qwen3.8-27B-NVFP4 MIXED_PRECISION | Fits | 33.813.5–37.2 | 35K | 26.4B | – | – | |
| Qwen/Qwen2.5-Coder-14B-Instruct Qwen/Qwen2.5-Coder-14B-Instruct-GGUF · Q4_K_M | Fits | 30.427.3–33.4 | 32K | 14.8B | – | – | |
| Qwen/Qwen2.5-32B-Instruct bartowski/Qwen2.5-32B-Instruct-GGUF · Q4_K_M | Fits | 25.823.2–28.3 | 32K | 32.8B | – | – | |
| Qwen/Qwen2.5-Coder-32B-Instruct bartowski/Qwen2.5-Coder-32B-Instruct-GGUF · Q4_K_M | Fits | 25.823.2–28.3 | 32K | 32.8B | – | – | |
| Qwen/Qwen3-32B unsloth/Qwen3-32B-GGUF · Q4_K_M | Fits | 25.522.9–28.0 | 35K | 32.8B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT wfakhri/OTel-2.0-LLM-31B-IT-GGUF · Q5_K_M | Fits | 23.120.8–25.4 | 38K | 31.3B | – | – | |
| zai-org/GLM-5.3 unsloth/GLM-5.3-GGUF · BF16 | Offload | 1.500.80–2.30 | 0 | 753.3B | p81 | p58 | |
| Qwen/Qwen3.5-122B-A10B unsloth/Qwen3.5-122B-A10B-GGUF · Q4_K_M | Offload | 14.67.30–22.0 | 256K | 125.1B | p77 | p49 | |
| zai-org/GLM-5 unsloth/GLM-5-GGUF · BF16 | Offload | 1.500.80–2.30 | 0 | 753.9B | p74 | p71 | |
| zai-org/GLM-5.1 unsloth/GLM-5.1-GGUF · BF16 | Offload | 1.500.80–2.30 | 0 | 753.9B | p53 | p68 | |
| Qwen/Qwen3.8-Flash-Next ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF · IQ3_XXS | Offload | 22.111.1–33.2 | 256K | 180B | p68 | p51 | |
| thinkingmachines/Inkling unsloth/inkling-GGUF · Q8_0 | Offload | 8.204.10–12.3 | 0 | 952.4B | p68 | p45 | |
| MiniMaxAI/MiniMax-M2.5 unsloth/MiniMax-M2.5-GGUF · UD-IQ2_M | Offload | 12.46.20–18.6 | 47K | 228.7B | p46 | p61 | |
| deepseek-ai/DeepSeek-V3.2 unsloth/DeepSeek-V3.2-GGUF · BF16 | Offload | 1.500.70–2.20 | 0 | 685.4B | p60 | p34 | |
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF · MXFP4_MOE | Offload | 10.15.10–15.2 | 254K | 123.6B | p50 | p15 | |
| openai/gpt-oss-120b unsloth/gpt-oss-120b-GGUF · F16 | Offload | 18.89.40–28.3 | 128K | 117B | p47 | p15 | |
| poolside/Laguna-S-2.1 Myric/Laguna-S-2.1-APEX-GGUF · V2 [quality] | Offload | 12.45.00–18.7 | 210K | 117.6B | – | p34 | |
| ornith-ai/Ornith-1.5-35B-A3B-FP8 COMPRESSED-TENSORS | Offload | 38.615.4–57.9 | 256K | 36B | – | – | |
| ornith-ai/Ornith-1.5-122B-GGUF Q4_K_M | Offload | 14.57.30–21.8 | 256K | 124.6B | – | – |
Quality = benchmark percentile against all indexed models (p50 = median). Speeds are single-user decode ranges.