| 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 | 136115–156 | 256K | 30.5B | p85 | – | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · Q5_K_M | Fits | 32.927.9–37.8 | 42K | 31.3B | p63 | – | |
| Qwen/Qwen3.5-27B unsloth/Qwen3.5-27B-GGUF · Q6_K | Fits | 35.229.9–40.5 | 43K | 27.8B | p60 | p46 | |
| Qwen/Qwen3.8-27B unsloth/Qwen3.8-27B-GGUF · Q4_1 | Fits | 42.836.4–49.3 | 112K | 27.8B | p59 | p33 | |
| Qwen/Qwen3.6-27B unsloth/Qwen3.6-27B-GGUF · Q6_K | Fits | 35.129.9–40.4 | 42K | 27.8B | p51 | p54 | |
| Qwen/Qwen3.5-35B-A3B unsloth/Qwen3.5-35B-A3B-GGUF · Q4_K_M | Fits | 218185–251 | 256K | 36B | p49 | p35 | |
| google/gemma-4-26B-A4B-it unsloth/gemma-4-26B-A4B-it-GGUF · MXFP4_MOE | Fits | 11799.6–135 | 256K | 25.8B | p49 | – | |
| Qwen/Qwen3.5-9B unsloth/Qwen3.5-9B-GGUF · Q8_0 | Fits | 84.872.0–97.5 | 256K | 9.7B | p46 | – | |
| ornith-ai/Ornith-1.5-9B BF16 | Fits | 47.619.0–52.4 | 150K | 9.7B | p46 | p24 | |
| Qwen/Qwen3.6-35B-A3B unsloth/Qwen3.6-35B-A3B-MTP-GGUF · MXFP4_MOE | Fits | 217185–250 | 256K | 36B | p43 | p41 | |
| openbmb/MiniCPM-V-4.7-35B-A3B openbmb/MiniCPM-V-4.7-35B-A3B-gguf · Q5_K_S | Fits | 211180–243 | 256K | 35.2B | p42 | – | |
| ornith-ai/Ornith-1.0-35B bartowski/deepreinforce-ai_Ornith-1.0-35B-GGUF · Q5_K_S | Fits | 211179–242 | 256K | 35.1B | – | p40 | |
| openai/gpt-oss-20b unsloth/gpt-oss-20b-GGUF · F16 | Fits | 219186–252 | 128K | 21.1B | p39 | p15 | |
| Qwen/Qwen3.5-4B BF16 | Fits | 79.932.0–87.9 | 256K | 4.7B | p39 | – | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · Q8_0 | Fits | 61.852.5–71.0 | 256K | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 BF16 | Fits | 80.932.3–88.9 | 109K | 4B | p38 | – | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 bartowski/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF · Q4_K_S | Fits | 174148–200 | 256K | 32.9B | p37 | p9 | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 MIXED_PRECISION | Fits | 17770.8–195 | 1M | 47.1B | p36 | p9 | |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 unsloth/Nemotron-3-Nano-30B-A3B-GGUF · Q5_K_S | Fits | 172146–198 | 256K | 31.6B | p33 | – | |
| poolside/Laguna-XS-2.1 poolside/Laguna-XS-2.1-GGUF · Q4_K_M | Fits | 216184–249 | 256K | 33.4B | – | p30 | |
| Qwen/Qwen2.5-7B BF16 | Fits | 58.423.3–64.2 | 128K | 7.6B | p29 | – | |
| google/gemma-4-E4B-it BF16 | Fits | 77.330.9–85.0 | 128K | 8B | p27 | – | |
| openbmb/MiniCPM5-2B BF16 | Fits | 13955.8–153 | 128K | 2.5B | p27 | p3 | |
| poolside/Laguna-XS.2 Lucebox/Laguna-XS.2-GGUF · Q4_K_M | Fits | 216184–249 | 256K | 33.4B | – | p25 | |
| Qwen/Qwen3.5-2B BF16 | Fits | 15260.9–168 | 256K | 2.3B | p24 | – | |
| ornith-ai/Ornith-1.0-9B unsloth/Ornith-1.0-9B-GGUF · Q8_0 | Fits | 85.072.2–97.7 | 256K | 9.4B | – | p20 | |
| google/gemma-4-E2B-it BF16 | Fits | 13453.5–147 | 128K | 5.1B | p18 | – | |
| Qwen/Qwen2.5-1.5B BF16 | Fits | 20883.2–229 | 128K | 1.5B | p15 | – | |
| mistralai/Mistral-7B-Instruct-v0.2 BF16 | Fits | 54.021.6–59.3 | 32K | 7.2B | p14 | – | |
| Qwen/Qwen2.5-0.5B BF16 | Fits | 486194–534 | 32K | 0.5B | p5 | – | |
| Qwen/Qwen3.5-0.8B BF16 | Fits | 279112–307 | 256K | 0.9B | p4 | – | |
| incoai/Qwen3.8-27B-DFlash2 BF16 | Fits | 632253–695 | 256K | 1.9B | – | – | |
| Qwen/Qwen2.5-0.5B-Instruct BF16 | Fits | 486194–534 | 32K | 0.5B | – | – | |
| baidu/Unlimited-OCR-2 AtomicChat/Unlimited-OCR-2-GGUF · BF16 | Fits | 325276–373 | 128K | 3.3B | – | – | |
| datalab-to/surya-ocr-2 BF16 | Fits | 315126–346 | 256K | 0.7B | – | – | |
| Qwen/Qwen3.5-0.8B-Base BF16 | Fits | 279112–307 | 256K | 0.9B | – | – | |
| Qwen/Qwen3-0.6B-Base BF16 | Fits | 24196.5–265 | 32K | 0.6B | – | – | |
| Qwen/Qwen3-0.6B BF16 | Fits | 22389.3–246 | 40K | 0.8B | – | – | |
| openbmb/MiniCPM-V-4.7-1B BF16 | Fits | 22389.1–245 | 256K | 1.6B | – | – | |
| nvidia/Qwen3.6-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 21485.6–235 | 256K | 34B | – | – | |
| ornith-ai/Ornith-1.5-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 21485.6–235 | 256K | 34B | – | – | |
| Qwen/Qwen2.5-1.5B-Instruct BF16 | Fits | 20883.2–229 | 32K | 1.5B | – | – | |
| ornith-ai/Ornith-1.0-35B-GGUF Q4_K_M | Fits | 198168–228 | 256K | 34.7B | – | – | |
| ornith-ai/Ornith-1.5-35B-A3B-GGUF Q4_K_M | Fits | 194165–223 | 256K | 35.5B | – | – | |
| Qwen/Qwen2-VL-2B-Instruct BF16 | Fits | 16164.3–177 | 32K | 2.2B | – | – | |
| Qwen/Qwen3-1.7B-Base BF16 | Fits | 15361.1–168 | 32K | 1.7B | – | – | |
| baidu/Unlimited-OCR BF16 | Fits | 15059.9–165 | 32K | 3.3B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 ijohn07/Qwen3-Coder-30B-A3B-Instruct-FP8-Q4_K_M-GGUF · Q4_K_M | Fits | 143122–164 | 232K | 30.5B | – | – | |
| openbmb/MiniCPM5-2B-GGUF F16 | Fits | 139118–160 | 128K | 2.5B | – | – | |
| Qwen/Qwen3-1.7B BF16 | Fits | 13955.5–153 | 40K | 2B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF · Q5_K_M | Fits | 136115–156 | 256K | 30.5B | – | – | |
| Qwen/Qwen3-30B-A3B unsloth/Qwen3-30B-A3B-GGUF · Q5_K_M | Fits | 136115–156 | 40K | 30.5B | – | – | |
| Qwen/Qwen3-VL-2B-Instruct BF16 | Fits | 13554.0–148 | 172K | 2.1B | – | – | |
| Qwen/Qwen2.5-3B-Instruct BF16 | Fits | 11646.4–128 | 32K | 3.1B | – | – | |
| Qwen/Qwen2.5-VL-3B-Instruct BF16 | Fits | 99.639.8–110 | 125K | 3.8B | – | – | |
| Qwen/Qwen2.5-7B-Instruct Qwen/Qwen2.5-7B-Instruct-GGUF · Q8_0 | Fits | 99.384.4–114 | 32K | 7.6B | – | – | |
| Qwen/Qwen2.5-VL-7B-Instruct unsloth/Qwen2.5-VL-7B-Instruct-GGUF · Q8_0 | Fits | 98.884.0–114 | 125K | 8.3B | – | – | |
| Qwen/Qwen2-VL-7B-Instruct ggml-org/Qwen2-VL-7B-Instruct-GGUF · Q8_0 | Fits | 98.884.0–114 | 32K | 8.3B | – | – | |
| prism-ml/Bonsai-27B-mlx-1bit MLX-1BIT | Fits | 95.838.3–105 | 256K | 26.4B | – | – | |
| nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF · BF16 | Fits | 95.881.4–110 | 256K | 4B | – | – | |
| ornith-ai/Ornith-1.5-9B-NVFP4 MIXED_PRECISION | Fits | 91.636.6–101 | 256K | 9B | – | – | |
| Qwen/Qwen2.5-Coder-7B-Instruct Qwen/Qwen2.5-Coder-7B-Instruct-GGUF · Q4_K_M | Fits | 88.375.1–102 | 32K | 7.6B | – | – | |
| HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive Q8_K_P | Fits | 85.534.2–94.1 | 128K | 7.5B | – | – | |
| ornith-ai/Ornith-1.0-9B-GGUF Q8_0 | Fits | 85.472.6–98.2 | 256K | 9B | – | – | |
| Qwen/Qwen3-8B-Base Qwen/Qwen3-Embedding-8B-GGUF · Q8_0 | Fits | 85.372.5–98.1 | 32K | 8.2B | – | – | |
| ornith-ai/Ornith-1.5-9B-GGUF Q8_0 | Fits | 83.070.5–95.4 | 256K | 9.2B | – | – | |
| Qwen/Qwen3-4B BF16 | Fits | 80.932.3–88.9 | 40K | 4B | – | – | |
| Qwen/Qwen3-8B unsloth/Qwen3-8B-GGUF · Q8_0 | Fits | 80.868.7–93.0 | 40K | 8.2B | – | – | |
| Qwen/Qwen3-VL-4B-Instruct Qwen/Qwen3-VL-4B-Instruct-GGUF · F16 | Fits | 80.868.7–92.9 | 109K | 4.4B | – | – | |
| Qwen/Qwen3-VL-8B-Instruct Qwen/Qwen3-VL-8B-Instruct-GGUF · Q8_0 | Fits | 80.568.5–92.6 | 108K | 8.8B | – | – | |
| Qwen/Qwen3.5-4B-Base BF16 | Fits | 79.932.0–87.9 | 256K | 4.7B | – | – | |
| prism-ml/Ternary-Bonsai-27B-mlx-2bit MLX-2BIT | Fits | 72.228.9–79.4 | 232K | 26.4B | – | – | |
| datalab-to/chandra-ocr-2 BF16 | Fits | 72.128.8–79.3 | 256K | 5.3B | – | – | |
| Qwen/Qwen3-14B unsloth/Qwen3-14B-GGUF · Q8_0 | Fits | 49.742.2–57.2 | 40K | 14.8B | – | – | |
| Qwen/Qwen2.5-14B-Instruct Qwen/Qwen2.5-14B-Instruct-GGUF · Q8_0 | Fits | 47.740.5–54.8 | 32K | 14.8B | – | – | |
| Qwen/Qwen2.5-Coder-14B-Instruct Qwen/Qwen2.5-Coder-14B-Instruct-GGUF · Q4_K_M | Fits | 43.036.5–49.4 | 32K | 14.8B | – | – | |
| RadixArk/Qwen3.8-27B-NVFP4 MIXED_PRECISION | Fits | 36.414.6–40.0 | 36K | 26.4B | – | – | |
| Qwen/Qwen2.5-32B-Instruct bartowski/Qwen2.5-32B-Instruct-GGUF · Q4_K_M | Fits | 36.230.8–41.6 | 32K | 32.8B | – | – | |
| Qwen/Qwen2.5-Coder-32B-Instruct bartowski/Qwen2.5-Coder-32B-Instruct-GGUF · Q4_K_M | Fits | 36.230.8–41.6 | 32K | 32.8B | – | – | |
| Qwen/Qwen3-32B unsloth/Qwen3-32B-GGUF · Q4_K_M | Fits | 36.030.6–41.4 | 35K | 32.8B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT wfakhri/OTel-2.0-LLM-31B-IT-GGUF · Q5_K_M | Fits | 32.627.7–37.5 | 38K | 31.3B | – | – | |
| zai-org/GLM-5.3 unsloth/GLM-5.3-GGUF · BF16 | Offload | 2.001.00–3.00 | 0 | 753.3B | p81 | p58 | |
| Qwen/Qwen3.5-122B-A10B unsloth/Qwen3.5-122B-A10B-GGUF · Q4_K_M | Offload | 19.39.60–28.9 | 256K | 125.1B | p77 | p49 | |
| zai-org/GLM-5 unsloth/GLM-5-GGUF · BF16 | Offload | 2.001.00–3.00 | 0 | 753.9B | p74 | p71 | |
| zai-org/GLM-5.1 unsloth/GLM-5.1-GGUF · BF16 | Offload | 2.001.00–3.00 | 0 | 753.9B | p53 | p68 | |
| Qwen/Qwen3.8-Flash-Next ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF · IQ3_XXS | Offload | 28.614.3–42.9 | 256K | 180B | p68 | p51 | |
| thinkingmachines/Inkling unsloth/inkling-GGUF · Q8_0 | Offload | 10.45.20–15.6 | 0 | 952.4B | p68 | p45 | |
| MiniMaxAI/MiniMax-M2.5 unsloth/MiniMax-M2.5-GGUF · UD-IQ2_M | Offload | 16.08.00–24.0 | 47K | 228.7B | p46 | p61 | |
| deepseek-ai/DeepSeek-V3.2 unsloth/DeepSeek-V3.2-GGUF · BF16 | Offload | 1.901.00–2.90 | 0 | 685.4B | p60 | p34 | |
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF · MXFP4_MOE | Offload | 13.36.70–20.0 | 256K | 123.6B | p50 | p15 | |
| openai/gpt-oss-120b unsloth/gpt-oss-120b-GGUF · F16 | Offload | 24.712.3–37.0 | 128K | 117B | p47 | p15 | |
| poolside/Laguna-S-2.1 Myric/Laguna-S-2.1-APEX-GGUF · V2 [quality] | Offload | 16.36.50–24.5 | 210K | 117.6B | – | p34 | |
| ornith-ai/Ornith-1.5-35B-A3B-FP8 COMPRESSED-TENSORS | Offload | 48.319.3–72.5 | 256K | 36B | – | – | |
| ornith-ai/Ornith-1.5-122B-GGUF Q4_K_M | Offload | 19.09.50–28.5 | 256K | 124.6B | – | – |
Quality = benchmark percentile against all indexed models (p50 = median). Speeds are single-user decode ranges.