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

GLM-4.7-Flash vs Gemma 4 12B

GLM-4.7-Flash scores higher on the intelligence index — 15 against 14. Gemma 4 12B is the smaller download at 7.1 GB, so it runs on cheaper hardware.

GLM-4.7-FlashGemma 4 12B
Intelligence index1514
ClassHaiku-classBelow every hosted tier
Weights18 GB7.1 GB
QuantisationQ4_K_MQ4_K_M
Parameters31.2B (3B active)12B
Max context198k256k
API price per 1M$0.061 in / $0.4 out$0.08 in / $0.13 out
LicenceMITApache 2.0
Cheapest machine that runs itStrix Halo Framework Desktop, 32GB $1,269Mac mini M6, 16GB $899
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.