Skip to content
Local AI Wizard
Your machine
Theme

Compare local AI models

Up to three models side by side, with sources.

Qwen3 Coder 30B A3BDevstral Small 2 24B

2 of 3 models

Memory needed

Q4 · each model's own figure, before any machine's reserve

No score in LiveBench 2026-06-25 for these models (not drawn, not zero) Not in LiveBench 2026-06-25

Q4 planning estimate: weights plus working room, before any machine's reserve; not a local measurement.

Specifications side by side

10 of 10 specifications

Specifications side by side
SpecificationQwen3 Coder 30B A3BDevstral Small 2 24B
PublisherAlibabaMistral
LicenseApache 2.0Apache 2.0
Task and abilitiesText & chatText & chatVision
Parameters31 B · 3.3B active24 B
Memory needed · Q4 · model onlyNeeds ~23 GBNeeds ~18 GB
Disk · Q4 weights~19 GB~15 GB
Context · tokens262,144262,144
LiveBench rank · open modelsNo score in this LiveBench releaseNo score in this LiveBench release
Measured speed4 published rowsNo published tokens-per-second measurement for this checkpoint
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.