| Model | Verdict | Decode tok/s | Max ctx | Size | Chat | Coding | |
|---|---|---|---|---|---|---|---|
| Qwen/Qwen3-30B-A3B-Instruct-2507 BF16 | Fits | 15361.1–168 | 256K | 30.5B | p85 | – | |
| zai-org/GLM-5.3 Scantist/GLM-5.3-SLIM-GGUF · UD-IQ2_M | Fits | 13453.6–147 | 860K | 753.3B | p81 | p58 | |
| deepseek-ai/DeepSeek-V4.1-Flash-1017 ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF · IQ2_XS | Fits | 18774.8–206 | 1M | 550.6B | p54 | p77 | |
| Qwen/Qwen3.5-122B-A10B unsloth/Qwen3.5-122B-A10B-GGUF · Q8_0 | Fits | 15361.2–168 | 256K | 125.1B | p77 | p49 | |
| Qwen/Qwen3.5-397B-A17B bartowski/Qwen_Qwen3.5-397B-A17B-GGUF · Q3_K_XL | Fits | 15562.2–171 | 256K | 403.4B | p74 | p54 | |
| zai-org/GLM-5.3-Flash unsloth/GLM-5.3-Flash-GGUF · UD-Q4_K_XL | Fits | 14256.6–156 | 1M | 321.3B | p74 | p49 | |
| zai-org/GLM-5 unsloth/GLM-5-GGUF · UD-TQ1_0 | Fits | 13453.5–147 | 198K | 753.9B | p74 | p71 | |
| tencent/Hy3 bartowski/Hy3-GGUF · Q4_K_L | Fits | 10341.2–113 | 245K | 298.8B | p73 | p46 | |
| zai-org/GLM-5.1 bartowski/zai-org_GLM-5.1-GGUF · IQ1_M | Fits | 13453.5–147 | 198K | 753.9B | p53 | p68 | |
| Qwen/Qwen3.8-Flash-Next unsloth/Qwen3.8-Flash-Next-GGUF · Q8_0 | Fits | 15461.5–169 | 256K | 180B | p68 | p51 | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · Q8_0 | Fits | 60.324.1–66.3 | 256K | 31.3B | p63 | – | |
| deepseek-ai/DeepSeek-V4-Flash FP8 | Fits | 16766.8–184 | 1M | 282.1B | p62 | p61 | |
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF · UD-Q2_K_XL | Fits | 13052.2–144 | 256K | 560.5B | p62 | p33 | |
| MiniMaxAI/MiniMax-M2.5 unsloth/MiniMax-M2.5-GGUF · Q6_K | Fits | 12549.9–137 | 192K | 228.7B | p46 | p61 | |
| Qwen/Qwen3.5-27B unsloth/Qwen3.5-27B-GGUF · Q8_0 | Fits | 76.230.5–83.8 | 256K | 27.8B | p60 | p46 | |
| deepseek-ai/DeepSeek-V3.2 unsloth/DeepSeek-V3.2-GGUF · UD-IQ1_M | Fits | 12650.2–138 | 160K | 685.4B | p60 | p34 | |
| Qwen/Qwen3.8-27B unsloth/Qwen3.8-27B-GGUF · Q8_0 | Fits | 75.430.2–82.9 | 256K | 27.8B | p59 | p33 | |
| thinkingmachines/Inkling-Small unsloth/Inkling-Small-GGUF · MXFP4_MOE | Fits | 13855.1–151 | 128K | 266B | p57 | p52 | |
| Qwen/Qwen3.6-27B unsloth/Qwen3.6-27B-GGUF · Q8_0 | Fits | 76.230.5–83.8 | 256K | 27.8B | p51 | p54 | |
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF · Q8_0 | Fits | 16164.5–177 | 256K | 123.6B | p50 | p15 | |
| Qwen/Qwen3.5-35B-A3B BF16 | Fits | 14758.6–161 | 256K | 36B | p49 | p35 | |
| google/gemma-4-26B-A4B-it BF16 | Fits | 14357.2–157 | 256K | 25.8B | p49 | – | |
| openai/gpt-oss-120b MXFP4 | Fits | 16465.6–180 | 128K | 117B | p47 | p15 | |
| Qwen/Qwen3.5-9B BF16 | Fits | 10441.6–114 | 256K | 9.7B | p46 | – | |
| ornith-ai/Ornith-1.5-9B BF16 | Fits | 10441.6–114 | 256K | 9.7B | p46 | p24 | |
| poolside/Laguna-M.1 linuxid10t/Laguna-M.1-GGUF · Q4_K_M | Fits | 10542.0–116 | 256K | 225.8B | – | p45 | |
| Qwen/Qwen3.6-35B-A3B BF16 | Fits | 14758.6–161 | 256K | 36B | p43 | p41 | |
| openbmb/MiniCPM-V-4.7-35B-A3B BF16 | Fits | 15762.9–173 | 256K | 35.2B | p42 | – | |
| ornith-ai/Ornith-1.0-35B BF16 | Fits | 15963.6–175 | 256K | 35.1B | – | p40 | |
| openai/gpt-oss-20b MXFP4 | Fits | 17670.3–193 | 128K | 21.1B | p39 | p15 | |
| deepseek-ai/DeepSeek-V4-Flash-0731 FP8 | Fits | 16465.8–181 | 1M | 282.1B | – | p39 | |
| Qwen/Qwen3.5-4B BF16 | Fits | 14056.2–155 | 256K | 4.7B | p39 | – | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · BF16 | Fits | 84.433.8–92.8 | 256K | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 BF16 | Fits | 13654.5–150 | 256K | 4B | p38 | – | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF · BF16 | Fits | 16766.8–184 | 256K | 32.9B | p37 | p9 | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 MIXED_PRECISION | Fits | 21184.4–232 | 1M | 47.1B | p36 | p9 | |
| poolside/Laguna-S-2.1 poolside/Laguna-S-2.1-GGUF · Q8_0 | Fits | 14758.9–162 | 1M | 117.6B | – | p34 | |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 unsloth/Nemotron-3-Nano-30B-A3B-GGUF · BF16 | Fits | 16766.9–184 | 256K | 31.6B | p33 | – | |
| poolside/Laguna-XS-2.1 BF16 | Fits | 16666.4–183 | 256K | 33.4B | – | p30 | |
| Qwen/Qwen2.5-7B BF16 | Fits | 11445.4–125 | 128K | 7.6B | p29 | – | |
| google/gemma-4-E4B-it BF16 | Fits | 13453.7–148 | 128K | 8B | p27 | – | |
| openbmb/MiniCPM5-2B BF16 | Fits | 17469.6–192 | 128K | 2.5B | p27 | p3 | |
| poolside/Laguna-XS.2 BF16 | Fits | 16666.4–183 | 256K | 33.4B | – | p25 | |
| Qwen/Qwen3.5-2B BF16 | Fits | 18272.6–200 | 256K | 2.3B | p24 | – | |
| ornith-ai/Ornith-1.0-9B BF16 | Fits | 10642.2–116 | 256K | 9.4B | – | p20 | |
| google/gemma-4-E2B-it BF16 | Fits | 17067.8–187 | 128K | 5.1B | p18 | – | |
| Qwen/Qwen2.5-1.5B BF16 | Fits | 19377.3–213 | 128K | 1.5B | p15 | – | |
| mistralai/Mistral-7B-Instruct-v0.2 BF16 | Fits | 10943.5–120 | 32K | 7.2B | p14 | – | |
| Qwen/Qwen2.5-0.5B BF16 | Fits | 22790.9–250 | 32K | 0.5B | p5 | – | |
| Qwen/Qwen3.5-0.8B BF16 | Fits | 21686.4–238 | 256K | 0.9B | p4 | – | |
| Qwen/Qwen2.5-0.5B-Instruct BF16 | Fits | 22790.9–250 | 32K | 0.5B | – | – | |
| incoai/Qwen3.8-27B-DFlash2 BF16 | Fits | 22690.4–249 | 256K | 1.9B | – | – | |
| datalab-to/surya-ocr-2 BF16 | Fits | 22288.7–244 | 256K | 0.7B | – | – | |
| Qwen/Qwen3.5-0.8B-Base BF16 | Fits | 21686.4–238 | 256K | 0.9B | – | – | |
| nvidia/Qwen3.6-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 21585.8–236 | 256K | 34B | – | – | |
| ornith-ai/Ornith-1.5-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 21585.8–236 | 256K | 34B | – | – | |
| baidu/Unlimited-OCR-2 AtomicChat/Unlimited-OCR-2-GGUF · BF16 | Fits | 21385.2–234 | 128K | 3.3B | – | – | |
| openbmb/MiniCPM-V-4.7-1B BF16 | Fits | 20481.7–225 | 256K | 1.6B | – | – | |
| Qwen/Qwen3-0.6B-Base BF16 | Fits | 20180.3–221 | 32K | 0.6B | – | – | |
| Qwen/Qwen3-0.6B BF16 | Fits | 19778.7–217 | 40K | 0.8B | – | – | |
| Qwen/Qwen2.5-1.5B-Instruct BF16 | Fits | 19377.3–213 | 32K | 1.5B | – | – | |
| Qwen/Qwen2-VL-2B-Instruct BF16 | Fits | 17971.5–197 | 32K | 2.2B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 FP8 | Fits | 17871.3–196 | 256K | 30.5B | – | – | |
| ornith-ai/Ornith-1.5-35B-A3B-FP8 COMPRESSED-TENSORS | Fits | 17871.2–196 | 256K | 36B | – | – | |
| Qwen/Qwen3-1.7B-Base BF16 | Fits | 17670.3–193 | 32K | 1.7B | – | – | |
| openbmb/MiniCPM5-2B-GGUF F16 | Fits | 17469.6–192 | 128K | 2.5B | – | – | |
| baidu/Unlimited-OCR BF16 | Fits | 17469.5–191 | 32K | 3.3B | – | – | |
| Qwen/Qwen3-1.7B BF16 | Fits | 17068.0–187 | 40K | 2B | – | – | |
| prism-ml/Bonsai-27B-mlx-1bit MLX-1BIT | Fits | 16967.4–185 | 256K | 26.4B | – | – | |
| Qwen/Qwen3-VL-2B-Instruct BF16 | Fits | 16867.3–185 | 256K | 2.1B | – | – | |
| ornith-ai/Ornith-1.0-35B-GGUF BF16 | Fits | 16666.4–183 | 256K | 34.7B | – | – | |
| ornith-ai/Ornith-1.5-35B-A3B-GGUF BF16 | Fits | 16565.9–181 | 256K | 35.5B | – | – | |
| Qwen/Qwen2.5-3B-Instruct BF16 | Fits | 16164.3–177 | 32K | 3.1B | – | – | |
| nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF · BF16 | Fits | 15863.1–174 | 256K | 4B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct BF16 | Fits | 15361.1–168 | 256K | 30.5B | – | – | |
| Qwen/Qwen3-30B-A3B BF16 | Fits | 15361.1–168 | 40K | 30.5B | – | – | |
| Qwen/Qwen2.5-VL-3B-Instruct BF16 | Fits | 15160.2–166 | 125K | 3.8B | – | – | |
| ornith-ai/Ornith-1.5-9B-NVFP4 MIXED_PRECISION | Fits | 15060.2–165 | 256K | 9B | – | – | |
| prism-ml/Ternary-Bonsai-27B-mlx-2bit MLX-2BIT | Fits | 14457.6–159 | 256K | 26.4B | – | – | |
| Qwen/Qwen3.5-4B-Base BF16 | Fits | 14056.2–155 | 256K | 4.7B | – | – | |
| Qwen/Qwen3-4B BF16 | Fits | 13654.5–150 | 40K | 4B | – | – | |
| ornith-ai/Ornith-1.5-122B-GGUF Q8_0 | Fits | 13654.2–149 | 256K | 124.6B | – | – | |
| HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive Q8_K_P | Fits | 13453.6–148 | 128K | 7.5B | – | – | |
| datalab-to/chandra-ocr-2 BF16 | Fits | 13353.2–146 | 256K | 5.3B | – | – | |
| Qwen/Qwen3-VL-4B-Instruct BF16 | Fits | 13252.7–145 | 256K | 4.4B | – | – | |
| ornith-ai/Ornith-1.5-122B-FP8 COMPRESSED-TENSORS | Fits | 12148.5–133 | 256K | 125.1B | – | – | |
| Qwen/Qwen2.5-7B-Instruct BF16 | Fits | 11445.4–125 | 32K | 7.6B | – | – | |
| Qwen/Qwen2.5-Coder-7B-Instruct BF16 | Fits | 11445.4–125 | 32K | 7.6B | – | – | |
| Qwen/Qwen2.5-VL-7B-Instruct BF16 | Fits | 10843.3–119 | 125K | 8.3B | – | – | |
| Qwen/Qwen2-VL-7B-Instruct BF16 | Fits | 10843.3–119 | 32K | 8.3B | – | – | |
| ornith-ai/Ornith-1.0-9B-GGUF BF16 | Fits | 10843.1–118 | 256K | 9B | – | – | |
| ornith-ai/Ornith-1.5-9B-GGUF BF16 | Fits | 10642.4–117 | 256K | 9.2B | – | – | |
| Qwen/Qwen3-8B BF16 | Fits | 10541.8–115 | 40K | 8.2B | – | – | |
| Qwen/Qwen3-8B-Base BF16 | Fits | 10541.8–115 | 32K | 8.2B | – | – | |
| Qwen/Qwen2.5-14B-Instruct Qwen/Qwen2.5-14B-Instruct-GGUF · Q8_0 | Fits | 10241.0–113 | 32K | 14.8B | – | – | |
| Qwen/Qwen3-VL-8B-Instruct BF16 | Fits | 10140.3–111 | 256K | 8.8B | – | – | |
| Qwen/Qwen2.5-Coder-14B-Instruct Qwen/Qwen2.5-Coder-14B-Instruct-GGUF · Q4_K_M | Fits | 95.738.3–105 | 32K | 14.8B | – | – | |
| RadixArk/Qwen3.8-27B-NVFP4 MIXED_PRECISION | Fits | 91.236.5–100 | 256K | 26.4B | – | – | |
| Qwen/Qwen3-14B BF16 | Fits | 73.029.2–80.3 | 40K | 14.8B | – | – | |
| Qwen/Qwen3-32B unsloth/Qwen3-32B-GGUF · Q8_0 | Fits | 61.724.7–67.9 | 40K | 32.8B | – | – | |
| Qwen/Qwen2.5-Coder-32B-Instruct Qwen/Qwen2.5-Coder-32B-Instruct-GGUF · Q4_K_M | Fits | 56.722.7–62.4 | 32K | 32.8B | – | – | |
| Qwen/Qwen2.5-32B-Instruct BF16 | Fits | 39.115.6–43.0 | 32K | 32.8B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT BF16 | Fits | 22.49.00–24.6 | 256K | 31.3B | – | – | |
| ornith-ai/Ornith-1.5-397B-GGUF Q4_K_M | Offload | 69.827.9–105 | 256K | 402.9B | – | – |
Quality = benchmark percentile against all indexed models (p50 = median). Speeds are single-user decode ranges.