| Model | Verdict | Decode tok/s | Max ctx | Size | Chat | Coding | |
|---|---|---|---|---|---|---|---|
| Qwen/Qwen3-30B-A3B-Instruct-2507 BF16 | Fits | 13453.7–148 | 256K | 30.5B | p85 | – | |
| Qwen/Qwen3.5-122B-A10B unsloth/Qwen3.5-122B-A10B-GGUF · Q4_K_M | Fits | 170145–196 | 256K | 125.1B | p77 | p49 | |
| zai-org/GLM-5.3-Flash peasantsmith/GLM-5.3-Flash-Maya-GGUF · IQ1_S | Fits | 20481.5–224 | 1M | 321.3B | p74 | p49 | |
| tencent/Hy3 bartowski/Hy3-GGUF · IQ1_M | Fits | 91.136.5–100 | 219K | 298.8B | p73 | p46 | |
| Qwen/Qwen3.8-Flash-Next ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF · IQ3_S | Fits | 155131–178 | 256K | 180B | p68 | p51 | |
| google/gemma-4-31B-it unsloth/gemma-4-31B-it-GGUF · Q8_0 | Fits | 44.337.6–50.9 | 256K | 31.3B | p63 | – | |
| MiniMaxAI/MiniMax-M2.5 unsloth/MiniMax-M2.5-GGUF · UD-IQ2_M | Fits | 96.982.4–112 | 192K | 228.7B | p46 | p61 | |
| Qwen/Qwen3.5-27B unsloth/Qwen3.5-27B-GGUF · Q8_0 | Fits | 51.944.1–59.7 | 256K | 27.8B | p60 | p46 | |
| Qwen/Qwen3.8-27B unsloth/Qwen3.8-27B-GGUF · Q8_0 | Fits | 51.343.6–59.0 | 256K | 27.8B | p59 | p33 | |
| thinkingmachines/Inkling-Small unsloth/Inkling-Small-GGUF · UD-IQ1_M | Fits | 161137–185 | 128K | 266B | p57 | p52 | |
| Qwen/Qwen3.6-27B unsloth/Qwen3.6-27B-GGUF · Q8_0 | Fits | 51.944.1–59.7 | 256K | 27.8B | p51 | p54 | |
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF · MXFP4_MOE | Fits | 128109–148 | 256K | 123.6B | p50 | p15 | |
| Qwen/Qwen3.5-35B-A3B BF16 | Fits | 13855.1–152 | 256K | 36B | p49 | p35 | |
| google/gemma-4-26B-A4B-it BF16 | Fits | 14457.6–158 | 256K | 25.8B | p49 | – | |
| openai/gpt-oss-120b unsloth/gpt-oss-120b-GGUF · F16 | Fits | 240204–277 | 128K | 117B | p47 | p15 | |
| Qwen/Qwen3.5-9B BF16 | Fits | 87.735.1–96.5 | 256K | 9.7B | p46 | – | |
| ornith-ai/Ornith-1.5-9B BF16 | Fits | 87.735.1–96.5 | 256K | 9.7B | p46 | p24 | |
| Qwen/Qwen3.6-35B-A3B BF16 | Fits | 13855.1–152 | 256K | 36B | p43 | p41 | |
| openbmb/MiniCPM-V-4.7-35B-A3B BF16 | Fits | 15461.7–170 | 256K | 35.2B | p42 | – | |
| ornith-ai/Ornith-1.0-35B BF16 | Fits | 15762.8–173 | 256K | 35.1B | – | p40 | |
| openai/gpt-oss-20b MXFP4 | Fits | 23292.7–255 | 128K | 21.1B | p39 | p15 | |
| deepseek-ai/DeepSeek-V4-Flash-0731 unsloth/DeepSeek-V4-Flash-0731-GGUF · UD-IQ1_S | Fits | 227193–261 | 1M | 282.1B | – | p39 | |
| Qwen/Qwen3.5-4B BF16 | Fits | 13955.5–153 | 256K | 4.7B | p39 | – | |
| google/gemma-4-12B-it unsloth/gemma-4-12b-it-GGUF · Q8_0 | Fits | 11093.8–127 | 256K | 12B | p38 | – | |
| Qwen/Qwen3-4B-Instruct-2507 BF16 | Fits | 14959.4–163 | 256K | 4B | p38 | – | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF · BF16 | Fits | 153130–176 | 256K | 32.9B | p37 | p9 | |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 MIXED_PRECISION | Fits | 22590.1–248 | 1M | 47.1B | p36 | p9 | |
| poolside/Laguna-S-2.1 Myric/Laguna-S-2.1-APEX-GGUF · V2 [quality] | Fits | 17168.5–188 | 1M | 117.6B | – | p34 | |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 unsloth/Nemotron-3-Nano-30B-A3B-GGUF · BF16 | Fits | 154131–177 | 256K | 31.6B | p33 | – | |
| poolside/Laguna-XS-2.1 BF16 | Fits | 17168.5–188 | 256K | 33.4B | – | p30 | |
| Qwen/Qwen2.5-7B BF16 | Fits | 11144.4–122 | 128K | 7.6B | p29 | – | |
| google/gemma-4-E4B-it BF16 | Fits | 14156.4–155 | 128K | 8B | p27 | – | |
| openbmb/MiniCPM5-2B BF16 | Fits | 22891.1–251 | 128K | 2.5B | p27 | p3 | |
| poolside/Laguna-XS.2 BF16 | Fits | 17168.5–188 | 256K | 33.4B | – | p25 | |
| Qwen/Qwen3.5-2B BF16 | Fits | 24999.8–274 | 256K | 2.3B | p24 | – | |
| ornith-ai/Ornith-1.0-9B BF16 | Fits | 89.835.9–98.7 | 256K | 9.4B | – | p20 | |
| google/gemma-4-E2B-it BF16 | Fits | 22991.5–252 | 128K | 5.1B | p18 | – | |
| Qwen/Qwen2.5-1.5B BF16 | Fits | 345138–380 | 128K | 1.5B | p15 | – | |
| mistralai/Mistral-7B-Instruct-v0.2 BF16 | Fits | 10341.2–113 | 32K | 7.2B | p14 | – | |
| Qwen/Qwen2.5-0.5B BF16 | Fits | 703281–773 | 32K | 0.5B | p5 | – | |
| Qwen/Qwen3.5-0.8B BF16 | Fits | 395158–435 | 256K | 0.9B | p4 | – | |
| incoai/Qwen3.8-27B-DFlash2 BF16 | Fits | 1167467–1284 | 256K | 1.9B | – | – | |
| Qwen/Qwen2.5-0.5B-Instruct BF16 | Fits | 703281–773 | 32K | 0.5B | – | – | |
| baidu/Unlimited-OCR-2 AtomicChat/Unlimited-OCR-2-GGUF · BF16 | Fits | 528449–607 | 128K | 3.3B | – | – | |
| datalab-to/surya-ocr-2 BF16 | Fits | 428171–471 | 256K | 0.7B | – | – | |
| Qwen/Qwen3-0.6B-Base BF16 | Fits | 401161–441 | 32K | 0.6B | – | – | |
| Qwen/Qwen3.5-0.8B-Base BF16 | Fits | 395158–435 | 256K | 0.9B | – | – | |
| Qwen/Qwen3-0.6B BF16 | Fits | 376151–414 | 40K | 0.8B | – | – | |
| Qwen/Qwen2.5-1.5B-Instruct BF16 | Fits | 345138–380 | 32K | 1.5B | – | – | |
| openbmb/MiniCPM-V-4.7-1B BF16 | Fits | 335134–369 | 256K | 1.6B | – | – | |
| Qwen/Qwen2-VL-2B-Instruct BF16 | Fits | 278111–306 | 32K | 2.2B | – | – | |
| nvidia/Qwen3.6-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 275110–302 | 256K | 34B | – | – | |
| ornith-ai/Ornith-1.5-35B-A3B-NVFP4 MIXED_PRECISION | Fits | 275110–302 | 256K | 34B | – | – | |
| baidu/Unlimited-OCR BF16 | Fits | 272109–299 | 32K | 3.3B | – | – | |
| Qwen/Qwen3-1.7B-Base BF16 | Fits | 272109–299 | 32K | 1.7B | – | – | |
| Qwen/Qwen3-1.7B BF16 | Fits | 25099.8–275 | 40K | 2B | – | – | |
| Qwen/Qwen3-VL-2B-Instruct BF16 | Fits | 24397.4–268 | 256K | 2.1B | – | – | |
| openbmb/MiniCPM5-2B-GGUF F16 | Fits | 228194–262 | 128K | 2.5B | – | – | |
| Qwen/Qwen2.5-3B-Instruct BF16 | Fits | 20180.3–221 | 32K | 3.1B | – | – | |
| ornith-ai/Ornith-1.5-35B-A3B-FP8 COMPRESSED-TENSORS | Fits | 19176.4–210 | 256K | 36B | – | – | |
| Qwen/Qwen2.5-VL-3B-Instruct BF16 | Fits | 17670.3–193 | 125K | 3.8B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 FP8 | Fits | 17068.0–187 | 256K | 30.5B | – | – | |
| ornith-ai/Ornith-1.0-35B-GGUF BF16 | Fits | 169143–194 | 256K | 34.7B | – | – | |
| ornith-ai/Ornith-1.5-35B-A3B-GGUF BF16 | Fits | 165140–190 | 256K | 35.5B | – | – | |
| ornith-ai/Ornith-1.5-9B-NVFP4 MIXED_PRECISION | Fits | 15662.4–172 | 256K | 9B | – | – | |
| nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF · BF16 | Fits | 155132–178 | 256K | 4B | – | – | |
| HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive Q8_K_P | Fits | 15361.1–168 | 128K | 7.5B | – | – | |
| Qwen/Qwen3-4B BF16 | Fits | 14959.4–163 | 40K | 4B | – | – | |
| ornith-ai/Ornith-1.5-122B-GGUF Q4_K_M | Fits | 147125–169 | 256K | 124.6B | – | – | |
| Qwen/Qwen3-VL-4B-Instruct BF16 | Fits | 13955.8–153 | 256K | 4.4B | – | – | |
| Qwen/Qwen3.5-4B-Base BF16 | Fits | 13955.5–153 | 256K | 4.7B | – | – | |
| prism-ml/Bonsai-27B-mlx-1bit MLX-1BIT | Fits | 13855.3–152 | 256K | 26.4B | – | – | |
| Qwen/Qwen3-Coder-30B-A3B-Instruct BF16 | Fits | 13453.7–148 | 256K | 30.5B | – | – | |
| Qwen/Qwen3-30B-A3B BF16 | Fits | 13453.7–148 | 40K | 30.5B | – | – | |
| datalab-to/chandra-ocr-2 BF16 | Fits | 12750.8–140 | 256K | 5.3B | – | – | |
| prism-ml/Ternary-Bonsai-27B-mlx-2bit MLX-2BIT | Fits | 11244.8–123 | 256K | 26.4B | – | – | |
| Qwen/Qwen2.5-7B-Instruct BF16 | Fits | 11144.4–122 | 32K | 7.6B | – | – | |
| Qwen/Qwen2.5-Coder-7B-Instruct BF16 | Fits | 11144.4–122 | 32K | 7.6B | – | – | |
| Qwen/Qwen2.5-VL-7B-Instruct BF16 | Fits | 10341.1–113 | 125K | 8.3B | – | – | |
| Qwen/Qwen2-VL-7B-Instruct BF16 | Fits | 10341.1–113 | 32K | 8.3B | – | – | |
| Qwen/Qwen3-8B-Base Qwen/Qwen3-Embedding-8B-GGUF · F16 | Fits | 10186.1–117 | 32K | 8.2B | – | – | |
| Qwen/Qwen3-8B BF16 | Fits | 95.538.2–105 | 40K | 8.2B | – | – | |
| Qwen/Qwen3-VL-8B-Instruct Qwen/Qwen3-VL-8B-Instruct-GGUF · F16 | Fits | 95.080.8–109 | 256K | 8.8B | – | – | |
| Qwen/Qwen3-14B unsloth/Qwen3-14B-GGUF · Q8_0 | Fits | 93.879.7–108 | 40K | 14.8B | – | – | |
| ornith-ai/Ornith-1.0-9B-GGUF BF16 | Fits | 92.778.8–107 | 256K | 9B | – | – | |
| ornith-ai/Ornith-1.5-9B-GGUF BF16 | Fits | 90.076.5–104 | 256K | 9.2B | – | – | |
| Qwen/Qwen2.5-14B-Instruct Qwen/Qwen2.5-14B-Instruct-GGUF · Q8_0 | Fits | 89.075.7–102 | 32K | 14.8B | – | – | |
| Qwen/Qwen2.5-Coder-14B-Instruct Qwen/Qwen2.5-Coder-14B-Instruct-GGUF · Q4_K_M | Fits | 80.968.7–93.0 | 32K | 14.8B | – | – | |
| RadixArk/Qwen3.8-27B-NVFP4 MIXED_PRECISION | Fits | 63.825.5–70.2 | 256K | 26.4B | – | – | |
| farbodtavakkoli/OTel-2.0-LLM-31B-IT wfakhri/OTel-2.0-LLM-31B-IT-GGUF · Q8_0 | Fits | 44.337.6–50.9 | 256K | 31.3B | – | – | |
| Qwen/Qwen3-32B unsloth/Qwen3-32B-GGUF · Q8_0 | Fits | 44.137.4–50.7 | 40K | 32.8B | – | – | |
| Qwen/Qwen2.5-Coder-32B-Instruct Qwen/Qwen2.5-Coder-32B-Instruct-GGUF · Q4_K_M | Fits | 40.134.1–46.1 | 32K | 32.8B | – | – | |
| Qwen/Qwen2.5-32B-Instruct BF16 | Fits | 26.110.5–28.8 | 32K | 32.8B | – | – | |
| Qwen/Qwen3.5-397B-A17B bartowski/Qwen_Qwen3.5-397B-A17B-GGUF · IQ2_M | Offload | 58.929.4–88.3 | 155K | 403.4B | p74 | p54 | |
| deepseek-ai/DeepSeek-V4-Flash antirez/deepseek-v4-gguf · V2 | Offload | 19477.4–290 | 1M | 282.1B | p62 | p61 | |
| poolside/Laguna-M.1 linuxid10t/Laguna-M.1-GGUF · Q4_K_M | Offload | 24.912.4–37.3 | 56K | 225.8B | – | p45 | |
| ornith-ai/Ornith-1.5-122B-FP8 COMPRESSED-TENSORS | Offload | 46.018.4–69.1 | 256K | 125.1B | – | – |
Quality = benchmark percentile against all indexed models (p50 = median). Speeds are single-user decode ranges.