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

Best AI models to run locally on a 2GB Mac

A leaderboard of the best AI models you can run locally on a Mac with 2GB of memory. LFM2.5 1.2B Thinking is #1 right now, followed by LFM2.5 1.2B Instruct and LFM2 1.2B. Models are ranked by one score that combines 575 published benchmarks. Each model shows the download that fits and the command to run it.

9 models · 575 benchmarks · updated
Filter by your hardware and budget → ~1GB fast · local only · 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][$0.02][$0.1][$0.5][$2][$10][$50][any]max per M
Filter by task
task[all tasks][agent tasks][coding][chat & writing][math][vision & documents][web search]
New #1s for your hardware:
orRSS

detecting your OS…

$ terminal

detecting your OS…

Run curl "whatmodel.sh/?ram=2&gpu=apple&max=0"to get this list in your terminal (add &format=json for agents).

Score vs release date

#modelscore↓where↓RAM↓speed↓context↓get itsources
#modelscore↓where↓RAM↓speed↓context↓get itsources
450LFM2.5 1.2B Thinking · 4-bit Liquid AI50±2local~1.3GB33kllama.cpp › LiquidAI/LFM2.5-1.2B-Thinking model cardEuroEval leaderboards (results collection), English generative leaderboard
583LFM2.5 1.2B Instruct · 4-bit Liquid AI45±2local~1.3GB33kllama.cpp › LiquidAI/LFM2.5-1.2B-Thinking model cardEuroEval leaderboards (results collection), English generative leaderboard
657LFM2 1.2B · 4-bit Liquid AI41±1local~1.3GB33kllama.cpp › LiquidAI/LFM2-1.2B model cardEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
697Qwen2.5 Coder 0.5B Instruct · 8-bit Alibaba39±1local~1.2GB33kLM Studio › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Aider code editing benchmark runs (old edit leaderboard)
707LFM2 700M · 4-bit Liquid AI38±1local~1GB33kllama.cpp › LiquidAI/LFM2-1.2B model cardEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
788Qwen2.5 0.5B Instruct · 4-bit Alibaba30±2local~1.2GB33kllama.cpp › HuggingFaceTB/SmolLM2-360M-Instruct model cardSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)Berkeley Function Calling Leaderboard result archiveOpen Portuguese LLM Leaderboard (archived)+1
808Qwen2 0.5B Instruct · 8-bit Alibaba28±2local~1.2GB32kllama.cpp › Qwen2-0.5B-Instruct model cardLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsOpen Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)Open Portuguese LLM Leaderboard (archived)
837SmolLM2 360M Instruct · 8-bit Hugging Face22±3local~1.2GB8kLM Studio › HuggingFaceTB/SmolLM2-360M-Instruct model cardEuroEval leaderboards (results collection), English generative leaderboard
849Gemma 3 270M IT · 4-bit Google17±4local~1.2GB32kllama.cpp › Google DeepMind Gemma 3 270M IT model cardEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)

+ 904 more don't fit your machine or budget · show them

+ 2 models with fewer than 3 results left off, since one or two tests say little about overall ability · show them

913 of 1219 catalogue models listed here · sources and licences

* new or thinly tested: ranked on too few benchmark results · † only the maker’s own numbers so far · ~RAM is estimated; full context may need more memory

9 models · 575 benchmarks · updated