GraySoft
Download guIDE →
Projects Models Compare Cloud benchmarks FAQ Download guIDE →

Alibaba cloud models

88 models tracked via Artificial Analysis. Compare cloud performance, then find local GGUF versions in the GraySoft model catalog.

ModelIntelligenceSpeed (tok/s)
Qwen3.8 Max40.340.841
Qwen3.8 2.4T A95B4040.214
Qwen3.8-Flash-Next39.952.574
Qwen3.8 27B (xhigh)33.944.452
Qwen3.7 Max29.90
Qwen3.6 Max Preview28.40
Qwen3.8 27B (medium)27.847.824
Qwen3.6 Plus270
Qwen3.8 27B (low)26.549.099
Qwen3.7 Plus25.860.77
Qwen3.5 27B (Reasoning)22.90
Qwen3.8 27B (Non-reasoning)22.449.66
Qwen3.6 27B (Reasoning)21.957.144
Qwen3.5 397B A17B (Non-reasoning)21.482.198
Qwen3 Max Thinking21.30
Qwen3.5 Omni Plus20.491.139
Qwen3.6 27B (Non-reasoning)19.857.753
Qwen3.5 27B (Non-reasoning)19.40
Qwen3.5 35B A3B (Reasoning)19.30
Qwen3.5 397B A17B (Reasoning)19.181.219
Qwen3.6 35B A3B (Reasoning)18.8136.769
Qwen3.5 122B A10B (Non-reasoning)17.7145.266
Qwen3 Max Thinking (Preview)16.30
Qwen3.5 122B A10B (Reasoning)16.2133.945
Qwen3 Max15.60
Qwen3.6 35B A3B (Non-reasoning)15.2141.038
Qwen3.5 35B A3B (Non-reasoning)15.1160.008
Qwen3.5 9B (Reasoning)13.786.444
Qwen3 VL 235B A22B (Reasoning)13.40
Qwen3.5 9B (Non-reasoning)13.390.128
Qwen3.5 4B (Reasoning)13.117.901
Qwen3 235B A22B 2507 (Reasoning)12.70
Qwen3 Max (Preview)12.60
Qwen3.5 Omni Flash12.5253.744
Qwen3 235B A22B 2507 Instruct120
Qwen3 Coder 480B A35B Instruct11.90
Qwen3 VL 32B (Reasoning)11.90
Qwen3 Next 80B A3B (Reasoning)11.2201.187
Qwen3.5 4B (Non-reasoning)10.825.499
Qwen3 Coder Next10.1119.018

Run models locally with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models