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

Best Decision models for document & agent workflows for a 32GB Mac

A leaderboard of the best Decision models for document & agent workflows for a Mac with 32GB of memory. Published typed-decision evaluations, with evaluator-specific protocols and tested settings retained. Each task score uses only its reviewed benchmarks. 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 workflows 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

  80 ┤ · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · ·●·Perplexity Decider v1.1 (… · · · ·
     │                ·               ·               ·               ·   │            ·               ·
     │   ◆─Jev 1.13───────────────────────────────────────────────────────┘  ◇         ◇               ◇  ◇
  60 ┤ · · · · · · · ··· · · · ·◇· · ··· · · · · · · ··· · · ∘ · · · ··· · · · · · · · · · · · · · · · · · · ·
     │                                ◇                      ∘
     └────────────────┬───────────────┬───────────────┬───────────────┬────────────────┬───────────────┬──────
                 2026-09-19      2026-09-24      2026-09-29      2026-10-04       2026-10-09      2026-10-14

Release dates available for 11 of 18 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	sources
1	Perplexity Decider v1.1 (27B) Perplexity	80±1	api price unknown		openrouter.ai ↗
3	Mercury Decide (paid endpoint) Inception	72±3	api price unknown		openrouter.ai ↗
8	Microsoft-Decision-1 Microsoft	66±2	api price unknown		openrouter.ai ↗
9	Jev 1.13 TypeSafe	65±1	api $0.042/M input tokens		docs.typesafe.ai ↗	+3
12	GPT-6 Luna Decisions OpenAI	64±2	api price unknown		openrouter.ai ↗
15	Jev 1.14 TypeSafe	63±2	api $0.042/M input tokens		docs.typesafe.ai ↗
17	d1-ultra Liquid AI	63±4*	api price unknown		openrouter.ai ↗
18	d1 (hosted) Liquid AI	62±2	api price unknown		openrouter.ai ↗
24	Clef Cloudflare	61±1	api $0.24/M input tokens	~68GB	developers.cloudflare.com ↗
31	Span-02 (Gemma 4 26B-A4B) Respan	60±4*	api price unknown		openrouter.ai ↗
33	d1.1 (hosted) Liquid AI	60±4*	api price unknown		openrouter.ai ↗
36	Mercury Decide (free endpoint) Inception	59±4*	api price unknown		openrouter.ai ↗
38	Solar Decide Upstage	59±3	api price unknown		openrouter.ai ↗
68	Clef-flash Cloudflare	53±1	api $0.038/M input tokens	~25GB	developers.cloudflare.com ↗	+1
70	Solar Decide Flash Upstage	52±2	api price unknown		openrouter.ai ↗
72	Span-01 Pro Respan	52±9	api price unknown		www.respan.ai ↗
73	Clef-omni Cloudflare	52±2	api $0.15/M input tokens	~87GB	developers.cloudflare.com ↗
74	baselabs joey-1 (2B) baselabs	52±4*	api price unknown		openrouter.ai ↗

+ 99 more don't fit your machine or budget · show them

117 of 117 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