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

Gemma 4 26B-A4B vs Qwen3.5 122B-A10B

Gemma 4 26B-A4B scores higher on the intelligence index — 17 against 16. Gemma 4 26B-A4B is the smaller download at 17 GB, so it runs on cheaper hardware.

Gemma 4 26B-A4BQwen3.5 122B-A10B
Intelligence index1716
ClassHaiku-classHaiku-class
Weights17 GB78 GB
QuantisationQ4_K_MUD-Q4_K_M
Parameters25.2B (3.8B active)125.1B (10B active)
Max context256k256k
API price per 1M$0.042 in / $0.22 out$0.26 in / $2.08 out
LicenceApache 2.0Apache 2.0
Cheapest machine that runs itStrix Halo Framework Desktop, 32GB $1,269Strix Halo Framework Desktop, 128GB $3,449
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.