Skip to content
Local AI Wizard
Your machine
Theme

Compare local AI models

Up to three models side by side, with sources.

Qwen3.8 27BQwen3.5 35B A3B

2 of 3 models

Quality by category

LiveBench 2026-06-25 · 0–100 · higher is better

  • Qwen3.8 27B
75.3Overall80.0Reasoning75.7Coding61.4Agentic coding86.2Math76.6Data analysis74.3Language72.7Instructions

Source: LiveBench · release of Jun 25, 2026 · checked Oct 18, 2026 · No score in this release (not drawn, not zero): Qwen3.5 35B A3B

Specifications side by side

10 of 10 specifications

Specifications side by side
SpecificationQwen3.8 27BQwen3.5 35B A3B
PublisherAlibabaAlibaba
LicenseApache 2.0Apache 2.0
Task and abilitiesText & chatVisionVideoText & chatVisionVideo
Parameters27 B35 B · 3B active
Memory needed · Q4 · model onlyNeeds ~21 GBNeeds ~27 GB
Disk · Q4 weights~17 GB~22 GB
Context · tokens262,144 · 1,000,000 extended262,144 · 1,010,000 extended
LiveBench rank · open models#11 of 23No score in this LiveBench release
Measured speed5 published rows3 published rows
SourceModel cardModel card

See which of these models run on your machine, well or slowly.

Published comparisons

Written comparisons with the same evidence, sources and limits.