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

Best Decision models for images & screens for a 16GB Mac

A leaderboard of the best Decision models for images & screens for a Mac with 16GB 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 → ~11GB 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 vision 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

     │   ◆─Jev 1.13──────────────────────────────────────────────────────────────────────────────d1-ultra─◆
     │                ·               ·               ·      ∘        ·                ·               ◇
  60 ┤ · · · · · · · · · · · · · · · · · · · · · · · · · · · ∘ · · · · · · · ◇ · · · · · · · · · · · · · · · ·
     │                ·               ·               ·               ·                ·               ·
     │                                                       ∘
     └────────────────┬───────────────┬───────────────┬───────────────┬────────────────┬───────────────┬──────
                 2026-09-19      2026-09-24      2026-09-29      2026-10-04       2026-10-09      2026-10-14

Release dates available for 7 of 13 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
1	d1-ultra Liquid AI	75±4	api price unknown		openrouter.ai ↗
2	d1.1 (hosted) Liquid AI	74±4	api price unknown		openrouter.ai ↗
3	Jev 1.13 TypeSafe	74±4	api $0.042/M input tokens		docs.typesafe.ai ↗
5	Jev 1.14 TypeSafe	71±4	api $0.042/M input tokens		docs.typesafe.ai ↗
6	Mercury Decide (free endpoint) Inception	70±4	api price unknown		openrouter.ai ↗
8	Clef Cloudflare	69±4	api $0.24/M input tokens	~68GB	developers.cloudflare.com ↗
9	Mercury Decide (paid endpoint) Inception	68±7*	api price unknown		openrouter.ai ↗
13	d1 (hosted) Liquid AI	64±7*	api price unknown		openrouter.ai ↗
14	Clef-flash Cloudflare	64±3	api $0.038/M input tokens	~25GB	developers.cloudflare.com ↗
17	Span-02 (Gemma 4 26B-A4B) Respan	63±3	api price unknown		openrouter.ai ↗
31	GPT-6 Luna Decisions OpenAI	58±3	api price unknown		openrouter.ai ↗
48	Clef-omni Cloudflare	47±2	api $0.15/M input tokens	~87GB	developers.cloudflare.com ↗
55	baselabs joey-1 (2B) baselabs	44±6*	api price unknown		openrouter.ai ↗

+ 66 more don't fit your machine or budget · show them

79 of 79 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