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

Best Decision models for arts & human taste for a 32GB Mac

A leaderboard of the best Decision models for arts & human taste for a Mac with 32GB of memory. Typed-choice results from the Decision Index 0.4.1 public suite. These are decisions over supplied options, not generated answers. 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 → ~21GB fast · reset

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

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

price[local][$0.05][$0.1][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 arts & human taste evaluations only. Compare scores within this task. Models without task measurements are excluded.

New #1s for your hardware:

orRSS

detecting your OS…

$ terminal

Score vs release date

  70 ┤ · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · ·Clef-omni·●· ·
     │            ·              ·              ·               ·              ·              ·           ∘
     │                                                                                                    ∘
  60 ┤ · · · · · ··· · · · · · · · · · · · · · ··· · · · · · · ··· · · · · · · · · · · · · · ··· · · · · ·│· ·
     │   ◆─Jev 1.13───────────────────────────────────────────────────────────────────────────────────────┘
     └────────────┬──────────────┬──────────────┬───────────────┬──────────────┬──────────────┬───────────────
             2026-09-17     2026-09-19     2026-09-22      2026-09-24     2026-09-27     2026-09-29

Release dates available for 4 of 6 models. Undated models are omitted; month-only dates are plotted at the start of the month.

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

#	model	task score↓	where↓	RAM↓	get it
22	Clef-omni Cloudflare	70±1	api $0.15/M input tokens	~87GB	developers.cloudflare.com ↗
24	Clef Cloudflare	69±1†	api $0.24/M input tokens	~68GB	developers.cloudflare.com ↗
35	baselabs joey-1 (2B) baselabs	66±1†	api price unknown		openrouter.ai ↗
44	Clef-flash Cloudflare	64±1†	api $0.038/M input tokens	~25GB	developers.cloudflare.com ↗
57	Span-02 (Gemma 4 26B-A4B) Respan	63±1†	api price unknown		openrouter.ai ↗
100	Jev 1.13 TypeSafe	55±1†	api $0.042/M input tokens		docs.typesafe.ai ↗

+ 241 more don't fit your machine or budget · show them

247 of 247 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