Sunk Cost sunkcost.ai Data checked 2026-09-03

LFM2.5 2.6B vs Devstral Small 2 24B

Neither has a clear lead on the index. LFM2.5 2.6B is the smaller download at 1.7 GB, so it runs on cheaper hardware.

LFM2.5 2.6BDevstral Small 2 24B
Intelligence index88
ClassBelow every hosted tierBelow every hosted tier
Weights1.7 GB14 GB
QuantisationQ4_K_MQ4_K_M
Parameters2.7B24B
Max context128k384k
API price per 1M$0 in / $0 out$0.02 in / $0.1 out
LicenceLFM 1.0 (see repo)Apache 2.0
Cheapest machine that runs itMac mini M6, 16GB $899Strix Halo Framework Desktop, 32GB $1,269
Summarising not rated not rated
Translation not rated not rated
Everyday coding not rated not rated
Reasoning & maths not rated not rated
Agentic work not rated not rated

Ratings are coarse on purpose. Speeds and pay-back depend on the machine — open either model's page for the full list, or see both against the frontier. Context is 32k throughout.