Find Your Model

Browse 0 open-weight models. Compare speed, quality, and compatibility across different hardware and tools.

Loading models...

Model benchmark pages

Qwen3.8-Flash-Next-oQ5e-mtp Qwen3.8-Flash-Next-oQ4e-mtp Qwen3.8-27B-UD-IQ3_S Qwen3.8-27B-oQ8e-mtp gpt-oss:20b Qwen3.8-27B-oQ4e-mtp Qwen3.8-Flash-Next-oQ4e-mtp-BF16PLE-v1 Nex-N2.5-mini-MLX-4bit qwen3.8:27b Qwen3.6-35B-A3B-IQ4_NL Qwen3.8-27B-oQ8e-fp16-mtp Qwen3.8-27B-Q4_K_XL gemma4:26b gemma4:26b-a4b-it-qat qwen/qwen3.6-35b-a3b qwen3.5:9b qwen3.6:latest glm-4.7-flash-unsloth:small-hotfixed-90kHEAT gemma4:31b qwen3.6:27b Qwen3.6-27B-MLX-8bit Qwen3.8-27B-4bit qwen3.8:27b-mlx qwen3-coder-next:latest C:\AI Models\unsloth\Qwen3.8-27B-GGUF\Qwen3.8-27B-UD-Q3_K_XL.gguf llama3.1:8b Qwen3.6-27B-UD-MLX-4bit mtplx-qwen38-27b-optimized-quality qwen3.8:latest qwen38-27b Ornith-1.5-35B-A3B-oQ8e-mtp gemma4:e4b Qwen3.6-35B-A3B-MLX-8bit Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS ling-oq8e unsloth/Qwen3.8-27B-GGUF:Q4_K_M ministral-3:14b Qwen3.6-27B-MLX-4bit Tiel-Coder-35B-A3B-MLX-oQ4e Tiel-Coder-35B-A3B-MLX-oQ4e-MTP qwen35_122b unsloth/Qwen3.8-27B-GGUF:IQ3_S qwen36-35b_VISION Qwen3.6-27B-MTPLX-Optimized-Speed Qwen3.8-Flash-Next-Dynamic-oQ4e-Q4GU-g64-BF16-PLE-MLX-mtp ling-oq4e Ornith-1.5-35B-A3B-oQ4e-mtp Qwen3.8-Flash-Next-GPTQ6Experts-Q6Attn-BF16-PLE-MLX-MTP-Q8-GPTQ4Head zai-org/glm-4.6v-flash mudler/Qwen3.6-35B-A3B-APEX-MTP-GGUF Qwen3.8-27B-oQ8-mtp Qwen3.8-27B-oQ4-mtp peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP Qwen3.8-27B-GSQ-RCO-IQ3_S muse-glimmer:latest ornith-1.5-9b Qwen3.8-27B-oQ4e-fp16-mtp Tiel-Coder-35B-A3B-MTP-UD-Q2_K_XL Ling-3.0-tiny-oQ8e qwen3:14b /models/hub/models--unsloth--Qwen3.8-27B-GGUF/snapshots/f1bfb127c64f7072bdd2cad55f258b9c8b2910fe/Qwen3.8-27B-UD-Q6_K_XL.gguf gemma-4-26B-A4B-it-UD-IQ4_NL Qwen3.8-9B-Q8_0:latest Ornith-1.5-35B-A3B-IQ4_XS Muse-Glimmer-30B-oQ8e nanbeige4.1-3b gemma4:12b qwen3.5-9b-mtp@q8_0 google/gemma-4-12b-qat Qwen3.8-27B-oQ2e-mtp google/gemma-4-12b qwen3.6-14b-a3b-fablevibes Qwen3.8-Flash-Next-Q6Experts-g128-Q6Attn-g64-BF16-PLE-MLX-MTP-Q8 ornith-1.0-9b unsloth/Qwen3.8-27B-GGUF:UD-Q8_K_XL unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF:UD-Q4_K_XL Qwen3.8-Flash-Next-Q5GU-Q6Attn-g64-BF16-PLE-MLX-MTP-Q8 qwen3-coder:30b gemma-4-31B-it-MLX-8bit K2-Horizon-MoVA-36B-A4B-MLX-4bit mtplx-flash-next-bare-speed Muse-Glimmer-30B-4bit Qwen3.8-27B-IQ3_XXS prism-ml/bonsai-27b qwen3.8:27b-mtp-q4_K_M Tiel-Coder-35B-A3B-Q4_K_S unsloth/Qwen3.8-Flash-Next-GGUF NVIDIA-Nemotron-3-Super-120B-A12B-OptiQ-2bit gpt-oss-20b-UD-Q8_K_XL Cyber-Tiel-Coder-35B-A3B-MTP-UD-IQ3_XXS qwen3.8-27b-UD-Q4_K_XL Dirk-Qwen3.8-27B-UD-IQ4_XS qwen3.6:35b google/gemma-4-26b-a4b-qat gemma-4-26b-a4b-q4kxl ling-tiny Qwen3-Coder-30B-A3B-Instruct-MLX-8bit qwen2.5-coder:7b-instruct gpt-oss-20b-Q4_K_M Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp Qwen3.8-27B-MTPLX-Optimized-Quality qwen3.8-27b@iq3_s qwen3:30b-thinking qwen3.8:27b-q4_K_M IFM--K2-Horizon-MoVA-36B-A4B /models/Qwen3.8-27B-UD-IQ4_XS.gguf Qwen3.8-27B-GSQ-RCO-IQ3_XXS-mtp LiquidAI/LFM2.5-350M-GGUF:F16 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-mlx-oQ8e Qwen3.5:4B/MTP@262K qwen3.5-9b-sushi-coder-rl unsloth/Qwen3.8-27B-GGUF:UD-Q5_K_S bartowski/Qwen_Qwen3-Coder-Next-GGUF:Q6_K_L Qwen3.8-27B-oQ3e-mtp openai/gpt-oss-120b gpt-oss-20b-UD-Q4_K_XL unsloth/Qwen3.8-27B-GGUF:UD-Q6_K_XL Ornith-1.5-9B-Q8_0 mtplx-qwen38-27b-optimized-speed Ornith-1.5-9B-MLX-8bit Ornith-1.0-35B-MTPLX qwen3-coder:latest qwen3.5:4b ornith:35b granite-4.2-8b-Q4_K_L qwen/qwen3.5-35b-a3b gemma4:latest gemma4-it-e4b-FLM:latest qwen3.8-27b-gsq-rco gpt-oss-20b-UD-Q6_K_XL Ornith-1.5-35B-A3B-MLX-8bit qwen3.8-27b@iq2_xxs qwen3.5:27b /home/polaris/models/Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL.gguf Ornith-1.5-35B-A3B-BigBang-oQ8e-mtp qwen3.6:27b-mlx LFM2.5-8B-A1B-MLX-8bit openai/gpt-oss-20b:2 Qwen3.6:35B-4bit devstral-small-2:latest Qwen3.8-Flash-Next-Q5GU-g64-Q6Down-g128-Q6Attn-BF16-PLE-MLX-MTP-Q8 Qwen3.8-27B-Uncensored-MLX Qwen3.8-27B-GPTQ-W4A16 Qwen3.6-35B-A3B-oQ8e-mtp Dirk-Qwen3.8-27B-GSQ-RCO-IQ3_S Ornith-1.5-9B-oQ8e mudler/Ornith-1.5-35B-A3B-APEX-MTP-GGUF qwen3.5:latest laguna-xs-2.1 perplexity-ai--pplx-computer-qwen-3-6-35b-a3b-mlx-20260709 huihui-qwen3.8-27b-abliterated-oq5e-mtp Qwen3.8:27B/MTP@180K gemma4:12b-mlx tiel-coder-35b-a3b Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit glm-4.7-flash:latest Qwen3.6-35B-A3B-Q4_K_XL Gemma4:E2B/QAT-MTP@131K lmstudio-community/lfm2.5-2.6b nvidia/nemotron-3-nano-4b ornith-1.0-35b Unsloth-Ornith-1.5-35B-A3B-UD-Q4_K_XL NVIDIA-Nemotron-3.5-Lightning-30B-A3B-8bit

Hardware benchmark pages

Apple M5 Max Apple M4 Max RX 7900 XTX RX 7900 Xt 7900 XTX 7900 Gre 7900m RTX 4080 Super RTX 5060 Plus RTX 5060 RTX 4070 Ti Super Apple M4 Pro Apple M2 Ultra RTX 3080 Apple M5 Pro RTX 5090 RTX 3080 Plus RTX 3080 Ti RX 7600 Xt RTX 5060 Ti Plus RTX 5080 RX 9070 9070 Xt 9070 Gre RTX 5070 Ti Apple M1 Apple M5 RTX 4090 Apple M4 RX 5600 Oem 5600 Xt 5700 5700 Xt Plus RX 9060 Xt Advanced Micro Devices Inc Ati Hawkpoint1 RX 6700 6700 Xt 6750 Xt 6800m 6850m Xt RTX 5060 Plus RTX 5070 RX 7700 Xt 7800 Xt 880m 890m Apple M2 Max RTX 5080 L4 Plus RTX Pro 6000 Blackwell Server Edition RX 6800 Xt RTX Pro 6000 Blackwell Max Q Workstation Edition RTX 5090 Plus RTX 5090 Plus RTX 5090 RTX 4060 Laptop RX 7900 Xt 7900 XTX 7900m Plus RX 7900 Xt 7900 XTX 7900m Gtx 1070 With Max Q Design Plus RX 7900 XTX Instinct Mi60 RTX 3080 Ti RTX 3060 Ti Apple M1 Max RTX 4070 Laptop L40s Plus L40s RTX 3090 Ti Plus RTX 3090 Ti Apple M3 Apple M2 Pro RTX 5090 Laptop RX 9060 Xt