| 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_S | Fits | 68.927.5–75.8 | 189K | 30.5B | p85 | – | |
| zai-org/GLM-5.3-Flash peasantsmith/GLM-5.3-Flash-Maya-GGUF · Q4_K_M | Fits | 13252.9–146 | 189K | 321.3B | p74 | p49 | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · UD-IQ2_XXS | Fits | 20.48.10–22.4 | 45K | 31.3B | p63 | – | |
| Qwen/Qwen3.5-27B bartowski/Qwen_Qwen3.5-27B-GGUF · IQ2_S | Fits | 21.88.70–24.0 | 37K | 27.8B | p60 | p46 | |
| Qwen/Qwen3.8-27B unsloth/Qwen3.8-27B-GGUF · UD-Q2_K_XL | Fits | 22.89.10–25.0 | 49K | 27.8B | p59 | p33 | |
| Qwen/Qwen3.6-27B unsloth/Qwen3.6-27B-GGUF · UD-IQ2_XXS | Fits | 23.99.60–26.3 | 36K | 27.8B | p51 | p54 | |
| Qwen/Qwen3.5-35B-A3B unsloth/Qwen3.5-35B-A3B-GGUF · UD-IQ2_XXS | Fits | 11746.9–129 | 256K | 36B | p49 | p35 | |
| google/gemma-4-26B-A4B-it unsloth/gemma-4-26B-A4B-it-GGUF · UD-IQ2_M | Fits | 50.420.2–55.5 | 256K | 25.8B | p49 | – | |
| Qwen/Qwen3.5-9B unsloth/Qwen3.5-9B-GGUF · Q8_0 | Fits | 26.510.6–29.1 | 91K | 9.7B | p46 | – | |
| ornith-ai/Ornith-1.5-9B bartowski/Ornith-1.5-9B-GGUF · Q8_0 | Fits | 26.410.6–29.1 | 90K | 9.7B | p46 | p24 | |
| openbmb/MiniCPM-V-4.7-35B-A3B AtomicChat/MiniCPM-V-4.7-35B-A3B-GGUF · IQ1_M | Fits | 12047.9–132 | 256K | 35.2B | p42 | – | |
| ornith-ai/Ornith-1.0-35B bartowski/deepreinforce-ai_Ornith-1.0-35B-GGUF · IQ2_XXS | Fits | 12148.4–133 | 256K | 35.1B | – | p40 | |
| Qwen/Qwen3.5-4B unsloth/Qwen3.5-4B-GGUF · Q8_0 | Fits | 43.817.5–48.2 | 205K | 4.7B | p39 | – | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · Q6_K | Fits | 22.89.10–25.1 | 75K | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 unsloth/Qwen3-4B-Instruct-2507-GGUF · Q8_0 | Fits | 34.513.8–37.9 | 48K | 4B | p38 | – | |
| Qwen/Qwen2.5-7B Mungert/Qwen2.5-7B-Instruct-1M-GGUF · Q8_0 | Fits | 28.111.2–30.9 | 68K | 7.6B | p29 | – | |
| google/gemma-4-E4B-it unsloth/gemma-4-E4B-it-GGUF · Q8_0 | Fits | 35.414.1–38.9 | 128K | 8B | p27 | – | |
| openbmb/MiniCPM5-2B BF16 | Fits | 41.316.5–45.4 | 128K | 2.5B | p27 | p3 | |
| poolside/Laguna-XS.2 poolside-laguna-hackathon/Piscina-XS.2-GGUF · IQ1 | Fits | 11244.8–123 | 249K | 33.4B | – | p25 | |
| Qwen/Qwen3.5-2B unsloth/Qwen3.5-2B-GGUF · BF16 | Fits | 52.921.1–58.1 | 256K | 2.3B | p24 | – | |
| ornith-ai/Ornith-1.0-9B unsloth/Ornith-1.0-9B-GGUF · Q8_0 | Fits | 26.510.6–29.2 | 91K | 9.4B | – | p20 | |
| google/gemma-4-E2B-it unsloth/gemma-4-E2B-it-GGUF · Q8_0 | Fits | 57.623.1–63.4 | 128K | 5.1B | p18 | – | |
| Qwen/Qwen2.5-1.5B BF16 | Fits | 56.822.7–62.5 | 128K | 1.5B | p15 | – | |
| Qwen/Qwen2.5-0.5B BF16 | Fits | 11646.3–127 | 32K | 0.5B | p5 | – | |
| Qwen/Qwen3.5-0.8B BF16 | Fits | 88.635.4–97.4 | 256K | 0.9B | p4 | – | |
| Qwen/Qwen2.5-0.5B-Instruct BF16 | Fits | 11646.3–127 | 32K | 0.5B | – | – | |
| incoai/Qwen3.8-27B-DFlash2 BF16 | Fits | 11244.8–123 | 256K | 1.9B | – | – | |
| datalab-to/surya-ocr-2 BF16 | Fits | 10140.3–111 | 256K | 0.7B | – | – | |
| Qwen/Qwen3.5-0.8B-Base BF16 | Fits | 88.635.4–97.4 | 256K | 0.9B | – | – | |
| baidu/Unlimited-OCR-2 AtomicChat/Unlimited-OCR-2-GGUF · BF16 | Fits | 82.833.1–91.1 | 128K | 3.3B | – | – | |
| baidu/Unlimited-OCR sahilchachra/Unlimited-OCR-GGUF · BF16 | Fits | 76.130.5–83.7 | 32K | 3.3B | – | – | |
| Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct-GGUF · Q8_0 | Fits | 75.530.2–83.1 | 32K | 1.5B | – | – | |
| openbmb/MiniCPM-V-4.7-1B BF16 | Fits | 69.427.8–76.3 | 256K | 1.6B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF · UD-IQ1_S | Fits | 68.627.4–75.4 | 189K | 30.5B | – | – | |
| Qwen/Qwen3-30B-A3B unsloth/Qwen3-30B-A3B-GGUF · UD-IQ1_S | Fits | 68.427.3–75.2 | 40K | 30.5B | – | – | |
| Qwen/Qwen3-0.6B-Base BF16 | Fits | 64.825.9–71.3 | 32K | 0.6B | – | – | |
| openbmb/MiniCPM5-2B-GGUF Q8_0 | Fits | 60.524.2–66.6 | 128K | 2.5B | – | – | |
| Qwen/Qwen3-0.6B BF16 | Fits | 60.424.2–66.4 | 40K | 0.8B | – | – | |
| Qwen/Qwen2-VL-2B-Instruct ggml-org/Qwen2-VL-2B-Instruct-GGUF · F16 | Fits | 56.722.7–62.4 | 32K | 2.2B | – | – | |
| nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF · Q8_0 | Fits | 52.821.1–58.1 | 256K | 4B | – | – | |
| Qwen/Qwen2.5-3B-Instruct Qwen/Qwen2.5-3B-Instruct-GGUF · Q8_0 | Fits | 48.919.6–53.8 | 32K | 3.1B | – | – | |
| Qwen/Qwen3-VL-2B-Instruct Qwen/Qwen3-VL-2B-Instruct-GGUF · F16 | Fits | 42.316.9–46.5 | 70K | 2.1B | – | – | |
| Qwen/Qwen3-1.7B-Base BF16 | Fits | 42.316.9–46.5 | 32K | 1.7B | – | – | |
| Qwen/Qwen3-1.7B BF16 | Fits | 38.615.4–42.4 | 40K | 2B | – | – | |
| prism-ml/Bonsai-27B-mlx-1bit MLX-1BIT | Fits | 37.815.1–41.6 | 93K | 26.4B | – | – | |
| Qwen/Qwen3-4B unsloth/Qwen3-4B-GGUF · Q8_0 | Fits | 34.513.8–37.9 | 40K | 4B | – | – | |
| Qwen/Qwen2.5-VL-3B-Instruct unsloth/Qwen2.5-VL-3B-Instruct-GGUF · BF16 | Fits | 33.513.4–36.9 | 125K | 3.8B | – | – | |
| ornith-ai/Ornith-1.5-9B-NVFP4 MIXED_PRECISION | Fits | 28.711.5–31.6 | 80K | 9B | – | – | |
| Qwen/Qwen2.5-7B-Instruct Qwen/Qwen2.5-7B-Instruct-GGUF · Q8_0 | Fits | 28.111.2–30.9 | 32K | 7.6B | – | – | |
| Qwen/Qwen2.5-VL-7B-Instruct unsloth/Qwen2.5-VL-7B-Instruct-GGUF · Q8_0 | Fits | 27.911.2–30.7 | 68K | 8.3B | – | – | |
| Qwen/Qwen2-VL-7B-Instruct ggml-org/Qwen2-VL-7B-Instruct-GGUF · Q8_0 | Fits | 27.911.2–30.7 | 32K | 8.3B | – | – | |
| ornith-ai/Ornith-1.0-9B-GGUF Q8_0 | Fits | 26.710.7–29.4 | 91K | 9B | – | – | |
| prism-ml/Ternary-Bonsai-27B-mlx-2bit MLX-2BIT | Fits | 26.210.5–28.8 | 43K | 26.4B | – | – | |
| ornith-ai/Ornith-1.5-9B-GGUF Q8_0 | Fits | 26.010.4–28.6 | 83K | 9.2B | – | – | |
| Qwen/Qwen2.5-Coder-7B-Instruct Qwen/Qwen2.5-Coder-7B-Instruct-GGUF · Q4_K_M | Fits | 25.110.0–27.6 | 32K | 7.6B | – | – | |
| HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive Q8_K_P | Fits | 25.110.0–27.6 | 112K | 7.5B | – | – | |
| datalab-to/chandra-ocr-2 prithivMLmods/chandra-ocr-2-MTP-Repacked · BF16 | Fits | 24.89.90–27.3 | 66K | 4.7B | – | – | |
| Qwen/Qwen3.5-4B-Base BF16 | Fits | 24.89.90–27.3 | 66K | 4.7B | – | – | |
| Qwen/Qwen3-8B-Base Qwen/Qwen3-Embedding-8B-GGUF · Q8_0 | Fits | 24.59.80–27.0 | 32K | 8.2B | – | – | |
| Qwen/Qwen3-VL-8B-Instruct Qwen/Qwen3-VL-8B-Instruct-GGUF · Q8_0 | Fits | 23.29.30–25.5 | 43K | 8.8B | – | – | |
| Qwen/Qwen3-8B unsloth/Qwen3-8B-GGUF · Q8_0 | Fits | 23.29.30–25.6 | 40K | 8.2B | – | – | |
| Qwen/Qwen3-VL-4B-Instruct Qwen/Qwen3-VL-4B-Instruct-GGUF · F16 | Fits | 23.29.30–25.6 | 43K | 4.4B | – | – | |
| Qwen/Qwen3-14B unsloth/Qwen3-14B-GGUF · Q4_K_M | Fits | 21.78.70–23.9 | 33K | 14.8B | – | – | |
| Qwen/Qwen2.5-Coder-14B-Instruct bartowski/Qwen2.5-Coder-14B-Instruct-GGUF · Q4_K_S | Fits | 21.48.60–23.6 | 32K | 14.8B | – | – | |
| Qwen/Qwen2.5-14B-Instruct bartowski/Qwen2.5-14B-Instruct-GGUF · Q4_K_S | Fits | 21.48.60–23.6 | 32K | 14.8B | – | – | |
| zai-org/GLM-5.3 unsloth/GLM-5.3-GGUF · UD-Q6_K_XL | Offload | 3.201.60–4.80 | 0 | 753.3B | p81 | p58 | |
| Qwen/Qwen3.5-122B-A10B unsloth/Qwen3.5-122B-A10B-GGUF · Q3_K_M | Offload | 19.07.60–28.6 | 256K | 125.1B | p77 | p49 | |
| Qwen/Qwen3.5-397B-A17B unsloth/Qwen3.5-397B-A17B-GGUF · BF16 | Offload | 4.401.80–6.60 | 0 | 403.4B | p74 | p54 | |
| zai-org/GLM-5 unsloth/GLM-5-GGUF · Q6_K | Offload | 3.601.80–5.30 | 0 | 753.9B | p74 | p71 | |
| tencent/Hy3 bartowski/Hy3-GGUF · Q8_0 | Offload | 3.301.60–4.90 | 0 | 298.8B | p73 | p46 | |
| zai-org/GLM-5.1 bartowski/zai-org_GLM-5.1-GGUF · Q6_K | Offload | 3.201.60–4.90 | 0 | 753.9B | p53 | p68 | |
| Qwen/Qwen3.8-Flash-Next ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF · IQ2_XS | Offload | 23.49.30–35.0 | 123K | 180B | p68 | p51 | |
| thinkingmachines/Inkling DevQuasar/thinkingmachines.Inkling-GGUF · Q4_K_M | Offload | 3.001.50–4.40 | 0 | 952.4B | p68 | p45 | |
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF · BF16 | Offload | 3.301.30–5.00 | 0 | 560.5B | p62 | p33 | |
| MiniMaxAI/MiniMax-M2.5 unsloth/MiniMax-M2.5-GGUF · Q8_0 | Offload | 12.16.00–18.1 | 0 | 228.7B | p46 | p61 | |
| deepseek-ai/DeepSeek-V3.2 unsloth/DeepSeek-V3.2-GGUF · Q6_K | Offload | 3.701.80–5.50 | 0 | 685.4B | p60 | p34 | |
| thinkingmachines/Inkling-Small unsloth/Inkling-Small-GGUF · Q8_0 | Offload | 12.46.20–18.6 | 0 | 266B | p57 | p52 | |
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 bartowski/nvidia_Nemotron-3-Super-120B-A12B-GGUF · IQ4_NL | Offload | 12.85.10–19.2 | 215K | 123.6B | p50 | p15 | |
| openai/gpt-oss-120b unsloth/gpt-oss-120b-GGUF · F16 | Offload | 17.38.70–26.0 | 128K | 117B | p47 | p15 | |
| poolside/Laguna-M.1 sigargv/Laguna-M.1-GGUF · Q8_0 | Offload | 4.302.20–6.50 | 0 | 225.8B | – | p45 | |
| Qwen/Qwen3.6-35B-A3B unsloth/Qwen3.6-35B-A3B-MTP-GGUF · Q8_0 | Offload | 28.111.2–42.1 | 256K | 36B | p43 | p41 | |
| openai/gpt-oss-20b MXFP4 | Offload | 13.55.40–20.2 | 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 | 23.89.50–35.6 | 256K | 32.9B | p37 | p9 | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 MIXED_PRECISION | Offload | 41.016.4–61.5 | 1M | 47.1B | p36 | p9 | |
| poolside/Laguna-S-2.1 Myric/Laguna-S-2.1-APEX-GGUF · V2 [compact] | Offload | 16.46.60–24.6 | 188K | 117.6B | – | p34 | |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 unsloth/Nemotron-3-Nano-30B-A3B-GGUF · Q8_0 | Offload | 23.89.50–35.7 | 256K | 31.6B | p33 | – | |
| poolside/Laguna-XS-2.1 poolside/Laguna-XS-2.1-GGUF · BF16 | Offload | 15.57.80–23.3 | 116K | 33.4B | – | p30 | |
| nvidia/Qwen3.6-35B-A3B-NVFP4 MIXED_PRECISION | Offload | 47.118.8–70.6 | 256K | 34B | – | – | |
| ornith-ai/Ornith-1.5-35B-A3B-NVFP4 MIXED_PRECISION | Offload | 47.118.8–70.6 | 256K | 34B | – | – | |
| ornith-ai/Ornith-1.0-35B-GGUF Q8_0 | Offload | 27.110.8–40.6 | 256K | 34.7B | – | – | |
| ornith-ai/Ornith-1.5-35B-A3B-GGUF Q8_0 | Offload | 26.510.6–39.7 | 256K | 35.5B | – | – | |
| ornith-ai/Ornith-1.5-35B-A3B-FP8 COMPRESSED-TENSORS | Offload | 22.79.10–34.1 | 256K | 36B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 FP8 | Offload | 17.77.10–26.5 | 94K | 30.5B | – | – | |
| ornith-ai/Ornith-1.5-397B-GGUF Q8_0 | Offload | 10.44.20–15.7 | 0 | 402.9B | – | – | |
| ornith-ai/Ornith-1.5-122B-GGUF BF16 | Offload | 7.403.00–11.1 | 0 | 124.6B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT wfakhri/OTel-2.0-LLM-31B-IT-GGUF · Q3_K_M | Offload | 3.301.60–4.90 | 0 | 31.3B | – | – | |
| Qwen/Qwen3-32B unsloth/Qwen3-32B-GGUF · Q2_K | Offload | 3.001.50–4.40 | 0 | 32.8B | – | – | |
| Qwen/Qwen2.5-32B-Instruct bartowski/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.