RunsOnMy ModelsGPUs & MacsAPI pricesVRAM calculatorNew

What AI models run on the Mac M4 Pro 24GB?

The Mac M4 Pro 24GB has 24 GB of unified memory (273 GB/s). About 16.1 GB is usable for a model. 199 of 285 open models we track fit at 8K context.

199models fit (8K ctx)
181still fit at 32K ctx
40Blargest that fits
273 GB/smemory bandwidth

Models that fit, largest first

ModelParamsBest quant (8K)Needs32K contextMax tok/s (est.)
flint40B (1.3B act.)Q2_K14.8 GBQ2_K582details
Maxwell V1 Flash37B (2.3B act.)Q2_K14.0 GBQ2_K321details
Hermes 4.3 36B36BQ2_K15.4 GBno20details
Seed OSS 36B Instruct36BQ2_K15.4 GBno20details
Qwen3.6 35B A3B36B (3.0B act.)Q2_K13.6 GBQ2_K243details
Ornith 1.5 35B A3B36B (3.0B act.)Q2_K13.2 GBQ2_K250details
Qwen3.5 35B A3B36B (3.0B act.)Q2_K13.6 GBQ2_K243details
Axion 1.0 35B35B (3.9B act.)Q2_K13.3 GBQ2_K187details
Qwen AgentWorld 35B A3B35B (3.0B act.)Q2_K13.1 GBQ2_K243details
Yi 34B 200K34BQ2_K16.0 GBno19details
Yi 34B34BQ2_K16.0 GBno19details
Yi 34B Chat34BQ2_K16.0 GBno19details
Yi 1.5 34B Chat34BQ2_K14.3 GBno21details
Nous Hermes 2 Yi 34B34BQ2_K14.8 GBno20details
DeepSeek R1 Distill Qwen 32B33BQ2_K14.2 GBno22details
Qwen3 32B33BQ2_K14.1 GBno22details
GLM Z1 32B 041433BQ2_K12.6 GBQ2_K22details
GLM 4 32B 041433BQ2_K12.6 GBQ2_K22details
granite 4.0 h small32B (8.8B act.)Q2_K11.7 GBQ2_K85details
gemma 4 31B it31BQ2_K13.9 GBno23details
GLM 4.7 Flash31B (4.6B act.)Q2_K11.7 GBQ2_K163details
Qwen3 Coder 30B A3B Instruct31B (3.0B act.)Q2_K11.9 GBQ2_K247details
North Mini Code 1.030B (3.3B act.)Q2_K12.0 GBQ2_K220details
Hy Memory 30B A3B30B (3.0B act.)Q2_K11.9 GBQ2_K243details
Muse Glimmer 30B30BQ2_K11.4 GBQ2_K24details
granite 4.2 30b29BQ2_K12.7 GBno25details
Qwen3.8 27B28BQ3_K_M14.0 GBQ2_K20details
Qwen3.6 27B28BQ3_K_M14.0 GBQ2_K20details
Qwen3.5 27B28BQ3_K_M14.0 GBQ2_K20details
gemma 3 27b it27BQ3_K_M14.4 GBQ2_K20details
Arete 27B27BQ3_K_M13.6 GBQ2_K21details
MiniMax H3 Image PE27BQ3_K_M13.8 GBQ2_K21details
Trinity Mini26B (2.0B act.)Q3_K_M12.3 GBQ3_K_M300details
GLiDE 27B26BQ3_K_M13.2 GBQ2_K21details
diffusiongemma 26B A4B it26B (4.0B act.)Q3_K_M13.2 GBQ3_K_M140details
gemma 4 26B A4B it26B (4.0B act.)Q3_K_M13.3 GBQ3_K_M138details
LFM2.5 24B A2B24B (2.0B act.)Q4_K_M14.3 GBQ3_K_M225details
ERNIE 4.5 21B A3B PT22BQ4_K_M13.5 GBQ3_K_M20details
ERNIE 4.5 21B A3B Thinking22BQ4_K_M13.5 GBQ3_K_M20details
gpt oss safeguard 20b22B (4.8B act.)F1613.8 GBF1689details
gpt oss 20b21B (4.2B act.)F1613.8 GBF1699details
Groot 19B A3B 26102319B (3.0B act.)Q4_K_M12.7 GBQ4_K_M142details
Kimi VL A3B Thinking 250616B (3.0B act.)Q6_K13.5 GBQ6_K111details
Kimi VL A3B Instruct16B (3.0B act.)Q6_K14.2 GBQ5_K_M105details
Kimi VL A3B Thinking16B (3.0B act.)Q6_K13.5 GBQ6_K111details
deepseek moe 16b base16B (2.8B act.)Q5_K_M13.9 GBQ2_K128details
LLaDA2.1 mini16B (1.4B act.)Q6_K13.4 GBQ6_K232details
Moonlight 16B A3B Instruct16B (3.0B act.)Q6_K14.2 GBQ5_K_M102details
DeepSeek Coder V2 Lite Instruct16B (2.7B act.)Q6_K13.9 GBQ5_K_M115details
DeepSeek V2 Lite16B (2.7B act.)Q6_K13.9 GBQ5_K_M115details
DeepSeek V2 Lite Chat16B (2.7B act.)Q6_K13.9 GBQ5_K_M115details
Qwen2.5 Coder 14B Instruct15BQ6_K13.5 GBQ3_K_M23details
DeepSeek R1 Distill Qwen 14B15BQ6_K13.5 GBQ3_K_M23details
Qwen3 14B15BQ6_K13.2 GBQ4_K_M23details
phi 415BQ6_K13.4 GBQ3_K_M23details
gemma 3 12b it12BQ8_013.4 GBQ6_K22details
Llama Guard 4 12B12BQ8_014.2 GBQ4_K_M21details
Llama 3.2 11B Vision Instruct11BQ8_011.6 GBQ6_K26details
Llama 3.2 11B Vision11BQ8_012.4 GBQ6_K24details
GLM 4.6V Flash10BQ8_010.3 GBQ8_027details
GLM 4.1V 9B Thinking10BQ8_010.3 GBQ8_027details
Step3 VL 10B10BQ8_09.9 GBQ8_031details
SenseNova Loop 9B Preview9.7BQ8_010.0 GBQ8_029details
Qwen3.5 9B9.7BQ8_010.0 GBQ8_029details
Ornith 1.5 9B9.7BQ8_010.0 GBQ8_029details
Qwen3.5 9B Base9.7BQ8_010.0 GBQ8_029details
MiMo V2.6 Distill Qwen 9B9.4BQ8_010.0 GBQ8_029details
glm 4 9b9.4BQ6_K13.4 GBno33details
internlm3 8b instruct8.8BQ8_09.7 GBQ8_029details
granite 4.2 8b8.8BQ8_010.5 GBQ8_029details
granite 4.1 8b8.8BQ8_010.5 GBQ8_029details
Qwen3 VL 8B Instruct8.8BQ8_09.9 GBQ8_031details
Molmo2 8B8.7BQ8_09.9 GBQ8_031details
LFM2.5 8B A1B8.5B (1.0B act.)Q8_09.1 GBQ8_0257details
Qwen2.5 VL 7B Instruct8.3BQ8_08.7 GBQ8_034details
UI TARS 1.5 7B8.3BQ8_08.7 GBQ8_034details
olmOCR 2 7B 10258.3BQ8_08.7 GBQ8_034details
olmOCR 7B 0225 preview8.3BQ8_08.7 GBQ8_034details
UI TARS 7B DPO8.3BQ8_08.7 GBQ8_034details
Qwen3 8B8.2BQ8_09.9 GBQ8_031details
DeepSeek R1 0528 Qwen3 8B8.2BQ8_09.9 GBQ8_031details
granite 3.3 8b instruct8.2BQ8_09.8 GBQ8_031details
granite 3.1 8b instruct8.2BQ8_09.8 GBQ8_031details
granite 3.2 8b instruct8.2BQ8_09.8 GBQ8_031details
Apertus 8B Instruct 25098.1BQ8_09.6 GBQ8_032details
Llama 3.1 8B Instruct8.0BQ8_09.6 GBQ8_032details
Llama 3.1 8B8.0BQ8_09.6 GBQ8_032details
Hermes 3 Llama 3.1 8B8.0BQ8_09.6 GBQ8_032details
DeepSeek R1 Distill Llama 8B8.0BQ8_09.6 GBQ8_032details
Meta Llama 3 8B Instruct8.0BQ8_09.6 GBQ8_032details
Meta Llama Guard 2 8B8.0BQ8_09.6 GBQ8_032details
Meta Llama 3.1 8B Instruct8.0BQ8_09.6 GBQ8_032details
Ling 3.0 tiny7.9B (1.4B act.)Q8_08.7 GBQ8_0185details
MiMo 7B RL7.8BQ8_09.4 GBQ8_034details
internlm2 5 7b chat7.7BQ8_09.2 GBQ8_033details
internlm2 chat 7b7.7BQ8_09.2 GBQ8_033details
Qwen2.5 7B Instruct7.6BQ8_08.7 GBQ8_034details
Qwen2.5 Coder 7B Instruct7.6BQ8_08.7 GBQ8_034details
DeepSeek R1 Distill Qwen 7B7.6BQ8_08.7 GBQ8_034details
Falcon H1R 7B7.6BQ8_08.5 GBQ8_034details
Olmo 3 7B Instruct7.3BQ8_010.3 GBQ8_035details
Olmo 3 1025 7B7.3BQ8_010.3 GBQ8_035details
Olmo 3 7B Think7.3BQ8_010.3 GBQ8_035details
Mistral 7B v0.17.2BQ8_08.6 GBQ8_035details
Mistral 7B Instruct v0.27.2BQ8_08.6 GBQ8_035details
Mistral 7B Instruct v0.17.2BQ8_08.6 GBQ8_035details
falcon 7b7.2BQ8_012.1 GBno36details
falcon 7b instruct7.2BQ8_011.8 GBno37details
granite 4.0 h tiny6.9B (1.5B act.)F1613.6 GBF1693details
OLMoE 1B 7B 09246.9B (1.3B act.)F1614.4 GBQ8_0106details
deepseek coder 7b instruct v1.56.9BQ8_011.2 GBno37details
deepseek coder 6.7b instruct6.7BQ8_011.1 GBno38details
deepseek coder 6.7b base6.7BQ8_011.1 GBno38details
Llama 2 7b hf6.7BQ8_011.1 GBno38details
Yi 6B 200K6.1BF1612.3 GBF1623details
Yi 6B6.1BF1612.3 GBF1623details
Molmo2 4B4.9BF1610.0 GBF1631details
WeVisOne VL 4B4.8BF1610.0 GBF1631details
Mage VL Cowork4.7BF1610.0 GBF1631details
Qianfan OCR4.7BF1610.1 GBF1631details
Qwen3.5 4B4.7BF169.0 GBF1632details
S5 nano4.7BF169.2 GBF1632details
LightOnOCR 3 4B4.5BF169.0 GBF1632details
SingVL S1 4B4.5BF169.0 GBF1632details
Intern Decision 4B4.5BF169.0 GBF1632details
Qwen3 VL 4B Instruct4.4BF169.3 GBF1634details
gemma 3 4b it4.3BF168.4 GBF1635details
medgemma 1.5 4b it4.3BF168.4 GBF1635details
medgemma 4b it4.3BF168.4 GBF1635details
gemma 3 4b pt4.3BF169.2 GBF1632details
Phi 3.5 vision instruct4.1BF1611.2 GBQ3_K_M33details
Qwen3 4B4.0BF169.3 GBF1634details
Qwen3 4B Instruct 25074.0BF169.3 GBF1634details
granite vision 4.1 4b4.0BF167.6 GBF1640details
Phi 4 mini instruct3.8BF168.9 GBF1636details
Phi 3 mini 4k instruct3.8BF1610.6 GBQ3_K_M36details
Phi 3.5 mini instruct3.8BF1610.6 GBQ3_K_M36details
Phi 3 mini 128k instruct3.8BF1610.6 GBQ3_K_M36details
Qwen2.5 VL 3B Instruct3.8BF166.7 GBF1644details
granite 4.2 3b3.7BF168.0 GBF1637details
granite 4.1 3b llmon preview3.7BF168.0 GBF1637details
Raon 1 nano3.5BF167.0 GBF1644details
granite 4.1 3b3.4BF167.6 GBF1640details
granite 4.0 micro3.4BF167.6 GBF1640details
DeepSeek OCR 23.4B (1.2B act.)F166.6 GBF16132details
deepseek vl2 tiny3.4B (1.2B act.)F167.4 GBF16116details
Unlimited OCR 23.3B (1.1B act.)F166.6 GBF16135details
Unlimited OCR3.3B (1.1B act.)F166.6 GBF16136details
DeepSeek OCR3.3B (1.1B act.)F166.6 GBF16136details
granite 3.1 3b a800m instruct3.3B (883M act.)F167.1 GBF16154details
Llama 3.2 3B Instruct3.2BF1613.5 GBQ8_021details
Llama 3.2 3B3.2BF167.5 GBF1642details
Hermes 3 Llama 3.2 3B3.2BF167.5 GBF1642details
d1 3B3.1BF1610.8 GBF1625details
LFM2.5 VL 3B3.1BF1610.8 GBF1625details
Qwen2.5 3B Instruct3.1BF166.7 GBF1644details
SmolLM3 3B3.1BF166.9 GBF1644details
SmolLM3 3B Base3.1BF166.9 GBF1644details
phi 22.8BF168.2 GBQ8_049details
LFM2.5 2.6B2.7BF1610.8 GBF1625details
granite 3.3 2b instruct2.5BF165.8 GBF1654details
MiniCPM5 2B2.5BF165.7 GBF1654details
WeVisOne VL 2B2.4BF165.4 GBF1667details
Qwen3.5 2B2.3BF164.5 GBF1672details
SmolVLM Instruct2.2BF165.4 GBF1675details
Qwen3 1.7B2.0BF164.8 GBF1679details
Qwen3.8 27B DSpine b162.0BF164.8 GBF1667details
d1 2B1.9BF167.2 GBF1639details
LFM3 VL 2B1.9BF167.2 GBF1639details
DeepSeek R1 Distill Qwen 1.5B1.8BF164.2 GBF1677details
LFM3 1.7B1.7BF167.2 GBF1639details
LFM3 1.7B Base1.7BF164.0 GBF1679details
SmolLM2 1.7B Instruct1.7BF165.2 GBF1680details
SmolLM2 1.7B1.7BF165.2 GBF1680details
SmolLM 1.7B1.7BF165.2 GBF1680details
granite 4.0 1b1.6BF164.3 GBF1684details
Qwen2.5 1.5B Instruct1.5BF163.8 GBF1688details
OLMo 2 0425 1B1.5BF164.4 GBF1692details
deepseek coder 1.3b instruct1.3BF164.5 GBF16101details
Llama 3.2 1B1.2BF163.2 GBF16110details
Llama 3.2 1B Instruct1.2BF165.5 GBF1655details
LFM2.5 1.2B Instruct1.2BF165.0 GBF1658details
HunyuanOCR1.1BF163.5 GBF16122details
PaddleOCR VL 1.6959MF162.5 GBF16142details
Qwen3.5 0.8B873MF162.4 GBF16180details
LightOnOCR 3 0.8B853MF162.4 GBF16180details
FastVLM 0.5B759MF162.2 GBF16180details
Qwen3 0.6B752MF162.7 GBF16228details
GOT OCR2 0716MF162.8 GBF16191details
Nemotron 3.5 Parse631MF161.9 GBF16209details
GOT OCR 2.0 hf561MF162.5 GBF16244details
SmolVLM2 500M Video Instruct507MF161.6 GBF16333details
SmolVLM 500M Instruct507MF161.6 GBF16333details
Qwen2.5 0.5B Instruct494MF161.7 GBF16276details
LFM2.5 VL 450M449MF161.9 GBF16192details
SmolLM2 360M Instruct362MF161.5 GBF16376details
SmolLM2 360M362MF161.5 GBF16376details
LFM2.5 350M354MF161.9 GBF16192details
LFM2 350M354MF161.4 GBF16385details

Just too big at 4-bit

These need up to 35% more memory than the Mac M4 Pro 24GB has at Q4_K_M and 8K context. A smaller quant or shorter context may work.

ModelQ4_K_M needsShort by
GLiDE 27B16.2 GB0.1 GB
MiniMax H3 Image PE16.8 GB0.7 GB
Qwen3.8 27B16.8 GB0.7 GB
Qwen3.5 27B17.0 GB0.9 GB
Qwen3.6 27B17.0 GB1.0 GB
diffusiongemma 26B A4B it17.1 GB1.0 GB
gemma 4 26B A4B it17.2 GB1.1 GB
gemma 3 27b it17.3 GB1.3 GB
Arete 27B17.4 GB1.3 GB
Muse Glimmer 30B17.9 GB1.8 GB
GLM 4.7 Flash18.2 GB2.1 GB
Hy Memory 30B A3B18.5 GB2.4 GB
Qwen3 Coder 30B A3B Instruct18.7 GB2.6 GB
granite 4.0 h small18.9 GB2.8 GB
granite 4.2 30b19.1 GB3.0 GB

Questions

What is the biggest model that runs on the Mac M4 Pro 24GB?

Of the models we track, the largest that fits at 8K context is flint (40B) at Q2_K, needing about 14.8 GB.

How much of the Mac M4 Pro 24GB's memory can a model use?

About 16 GB of 24 GB. macOS lets the GPU use about 67% of unified memory by default; this can be raised with the iogpu.wired_limit_mb setting.

Spec source: Apple specifications. Model data: Hugging Face Hub API. Speed is a bandwidth ceiling (bandwidth ÷ bytes read per token), not a benchmark. Methodology · Report an error.