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

Best decision models for a 128GB Mac

A leaderboard of the best decision models for a Mac with 128GB of memory. Models are ranked by one score that combines 238 published benchmarks. Models that run on it show the download that fits and the command to run it.

18 models · 238 benchmarks · updated

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 → ~96GB 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]
New #1s for your hardware:
orRSS

detecting your OS…

$ terminal

detecting your OS…

Run curl "whatmodel.sh/decision?ram=128&gpu=apple&max=any"to get this list in your terminal (add &format=json for agents).

Score vs release date

Release dates available for 11 of 18 models. Undated models are omitted; month-only dates are plotted at the start of the month.

#modelscore↓where↓RAM↓speed↓get itsources
#modelscore↓where↓RAM↓speed↓get itsources
10Perplexity Decider v1.1 (27B) Perplexity72±1api price unknownopenrouter.ai ↗DecisionPivot · StartLux LabsLeanMCP · JevBenchDecision Models as Judges for Hallucination DetectionFreyer et al. · MedQACitead GEO Citation Benchmark (October 2026)
21d1-ultra Liquid AI69±2api price unknownopenrouter.ai ↗System One Bench (Ali Alhashimi)Etsabary · decision benchmarksCommit or Abstain? System One Decision Models, LLMs, and Missing Legal AuthorityDo We Need an LLM to Know Why Sources Conflict? Decision Models for Knowledge-Conflict Typing in RAG
32d1.1 (hosted) Liquid AI68±2api price unknownopenrouter.ai ↗System One Bench (Ali Alhashimi)Etsabary · decision benchmarks
49Jev 1.13 TypeSafe66±1api $0.042/M input tokensdocs.typesafe.ai ↗DecisionPivot · StartLux LabsDecision Index 0.4.1LeanMCP · JevBenchHanno Labs DecisionBench v1 reviewed resultsSystem One Bench (Ali Alhashimi)Etsabary · decision benchmarks+11
50Span-02 (Gemma 4 26B-A4B) Respan66±1api price unknownopenrouter.ai ↗Decision Index 0.4.1System One Bench (Ali Alhashimi)Etsabary · decision benchmarksDecision Index Vision 0.4
56Mercury Decide (paid endpoint) Inception65±1api price unknownopenrouter.ai ↗LeanMCP · JevBenchEtsabary · decision benchmarksFreyer et al. · MedQAPerch benchmark results
61d1 (hosted) Liquid AI65±1api price unknownopenrouter.ai ↗LeanMCP · JevBenchEtsabary · decision benchmarksSystem One Bench (Ali Alhashimi)Decision Models as Judges for Hallucination DetectionDo We Need an LLM to Know Why Sources Conflict? Decision Models for Knowledge-Conflict Typing in RAGFreyer et al. · MedQA+1
63Jev 1.14 TypeSafe64±1api $0.042/M input tokensdocs.typesafe.ai ↗System One Bench (Ali Alhashimi)Etsabary · decision benchmarksJevalKit (Valen Team)Decision Index 0.4.1Commit or Abstain? System One Decision Models, LLMs, and Missing Legal AuthorityDo We Need an LLM to Know Why Sources Conflict? Decision Models for Knowledge-Conflict Typing in RAG+1
74Clef Cloudflare63±1api $0.24/M input tokens~68GBdevelopers.cloudflare.com ↗DecisionPivot · StartLux LabsDecision Index 0.4.1LeanMCP · JevBenchSystem One Bench (Ali Alhashimi)Etsabary · decision benchmarksDecision Models as Judges for Hallucination Detection+4
76Microsoft-Decision-1 Microsoft63±1api price unknownopenrouter.ai ↗LeanMCP · JevBenchSystem One Bench (Ali Alhashimi)Etsabary · decision benchmarksDo We Need an LLM to Know Why Sources Conflict? Decision Models for Knowledge-Conflict Typing in RAGFreyer et al. · MedQAPerch benchmark results
77Mercury Decide (free endpoint) Inception63±2api price unknownopenrouter.ai ↗System One Bench (Ali Alhashimi)Benchmark Heaven (own decision evaluations)
94GPT-6 Luna Decisions OpenAI62±1api price unknownopenrouter.ai ↗LeanMCP · JevBenchSystem One Bench (Ali Alhashimi)Etsabary · decision benchmarksDecision Models as Judges for Hallucination DetectionDecideBench (Cho Yin Yong)DecisionModelHub · support benchmarks+4
121Clef-omni Cloudflare59±1api $0.15/M input tokens~87GBdevelopers.cloudflare.com ↗Decision Index 0.4.1LeanMCP · JevBenchSystem One Bench (Ali Alhashimi)Etsabary · decision benchmarksDecision Index Vision 0.4Freyer et al. · MedQA
134Clef-flash Cloudflare58±1api $0.038/M input tokens~25GBdevelopers.cloudflare.com ↗DecisionPivot · StartLux LabsDecision Index 0.4.1LeanMCP · JevBenchSystem One Bench (Ali Alhashimi)Etsabary · decision benchmarksDecideBench (Cho Yin Yong)+6
146Solar Decide Upstage57±1api price unknownopenrouter.ai ↗LeanMCP · JevBenchSystem One Bench (Ali Alhashimi)Freyer et al. · MedQA
190baselabs joey-1 (2B) baselabs52±1api price unknownopenrouter.ai ↗Decision Index 0.4.1Etsabary · decision benchmarksSystem One Bench (Ali Alhashimi)
207Span-01 Pro Respan50±9api price unknownwww.respan.ai ↗Perch benchmark results
223Solar Decide Flash Upstage48±1api price unknownopenrouter.ai ↗LeanMCP · JevBenchSystem One Bench (Ali Alhashimi)Etsabary · decision benchmarksFreyer et al. · MedQA

+ 339 more don't fit your machine or budget · show them

357 of 357 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

18 models · 238 benchmarks · updated