whatmodel.sh · find the best decision models you can run

Best Decision models for probability consistency for a 32GB graphics card

A leaderboard of the best Decision models for probability consistency for a 32GB graphics card (with 32GB of system RAM). JevBench mini probability-law pass rates. These measure coherence, not correctness; see the separate accuracy measurement on model pages. Models that run on it show the download that fits and the command to run it.

Compare tested decision models and inference recipes across text, vision and workflow tasks. Use task filters and raw results: probability consistency measures coherence, not correctness.

Filter by your hardware and budget → ~32GB fast · reset

ram[2][4][8][16][24][32][48][64][96][128][192][256]GB

gpu[apple silicon][graphics card][unified memory][none]

vram[4][8][12][16][24][32][48][64][80][96][128]GB

price[local][any]max per M input tokens

Filter by task

task[all tasks][tools & automation][retrieval & classification][language understanding][arts & human taste][knowledge & reasoning][vision][workflows][consistency]

Scores use reviewed consistency evaluations only. Compare scores within this task. Models without task measurements are excluded.

New #1s for your hardware:

orRSS

detecting your OS…

$ terminal

#	model	task score↓	where↓	RAM↓	speed↓	get it	sources

#	model	task score↓	where↓	RAM↓	speed↓	get it	sources
—	Jev 1.13 TypeSafe	not yet calibrated	api $0.042/M input tokens			docs.typesafe.ai ↗

+ 23 more don't fit your machine or budget · show them

24 of 24 catalogue models listed here · sources and licences

* new or thinly tested: ranked on too few benchmark results · † no independently run results verified · ~RAM is estimated; full context may need more memory