Macbook Unified Memory

Best local text models for MacBook 24gb

If you are searching for the best text model for MacBook 24GB, this compatibility index displays all open-source Large Language Models (LLMs) that fit your system at a baseline context length of 8,192 tokens. Compare quantization formats (FP16, Q8, Q4) to prevent CUDA OOM crashes.

Supported GPU Configurations & Tiers:

Apple M2/M3 Macbook Pro (24GB)Apple M2/M3 Macbook Air (24GB)

Compatible Local LLMs (20)

Meta30B params

Muse Glimmer 30B

FP16OOM

Q8_0OOM

Q4_K_MFits in Memory

Meta8B params

Llama-3.1 8B (Instruct)

FP16Fits in Memory

Q8_0Fits in Memory

Q4_K_MFits in Memory

Mistral AI7B params

Mistral 7B v0.3

FP16Fits in Memory

Q8_0Fits in Memory

Q4_K_MFits in Memory

Mistral AI22B params

Codestral 22B

FP16OOM

Q8_0OOM

Q4_K_MFits in Memory

Mistral AI3B params

Ministral 3 3B (Instruct)

FP16Fits in Memory

Q8_0Fits in Memory

Q4_K_MFits in Memory

Mistral AI8B params

Ministral 3 8B

FP16Fits in Memory

Q8_0Fits in Memory

Q4_K_MFits in Memory

Mistral AI14B params

Ministral 3 14B

FP16Fits in Memory

Q8_0OOM

Q4_K_MFits in Memory

Google2.3B params

Gemma 4 E2B

FP16Fits in Memory

Q8_0Fits in Memory

Q4_K_MFits in Memory

Google4.5B params

Gemma 4 E4B

FP16Fits in Memory

Q8_0Fits in Memory

Q4_K_MFits in Memory

Google11.95B params

Gemma 4 12B

FP16OOM

Q8_0Fits in Memory

Q4_K_MFits in Memory

Google25.2B params

Gemma 4 26B A4B

FP16OOM

Q8_0OOM

Q4_K_MFits in Memory

OpenAI21B params

gpt-oss-20b

FP16Fits in Memory

Q8_0N/A

Q4_K_MN/A

ornith-ai8.2B params

Ornith-1.5-9B

FP16Fits in Memory

Q8_0Fits in Memory

Q4_K_MFits in Memory

Alibaba Cloud (Qwen)8.2B params

Qwen3.5-9B

FP16Fits in Memory

Q8_0Fits in Memory

Q4_K_MFits in Memory

Alibaba Cloud (Qwen)3.7B params

Qwen3.5-4B

FP16Fits in Memory

Q8_0Fits in Memory

Q4_K_MFits in Memory

Alibaba Cloud (Qwen)1.7B params

Qwen3.5-2B

FP16Fits in Memory

Q8_0N/A

Q4_K_MN/A

Bespoke Labs8.21B params

Bespoke-Nimble-9B-v3

FP16OOM

Q8_0Fits in Memory

Q4_K_MFits in Memory

Inclusion AI7.9B params

Ling-3.0-tiny

FP16Fits in Memory

Q8_0Fits in Memory

Q4_K_MFits in Memory

Liquid AI24B params

LFM2.5-24B A2B

FP16OOM

Q8_0OOM

Q4_K_MFits in Memory

Openbmb0.9B params

MiniCPM V-4.7-1B

FP16Fits in Memory

Q8_0Fits in Memory

Q4_K_MN/A