MacBook Pro local LLM memory: what each size runs
Apple lists 16 GB as the smallest MacBook Pro and 128 GB as the largest, in both the 14-inch and 16-inch sizes. At the default macOS GPU share, the smallest MacBook Pro gives the GPU about 11 GiB and the largest gives about 96 GiB. On the largest configuration, the biggest model in our list that runs is GLM-4.5-Air at Q5_K_M (79.3 GiB–81.4 GiB at 8,192 tokens). On the smallest, it is Mistral-Nemo-Instruct-2407 at Q4_K_M.
Chips and memory sizes Apple lists
| Chip | GPU | Memory bandwidth | Unified memory |
|---|---|---|---|
| Apple M5 | 10-core GPU | 153 GB/s | 16 GB, 24 GB, 32 GB (The M5 is offered in the 14-inch model only.) |
| Apple M5 Pro | 16-core GPU, or 20-core GPU | 307 GB/s | 24 GB, 48 GB, 64 GB |
| Apple M5 Max (18-core CPU) | 32-core GPU, or 40-core GPU | 460 GB/s (614 GB/s with the 40-core GPU) | 36 GB, 48 GB, 64 GB, 128 GB (128 GB goes with the M5 Max 40-core GPU.) |
From Apple's MacBook Pro technical specifications, read 2026-10-18. Check that page before buying: Apple ties some memory sizes to a specific chip configuration. Bandwidth is Apple's figure. This site does not turn it into tokens per second and has no measurement on these machines.
What each memory size runs
| Unified memory | GPU budget | Models that run | Tight | Largest that runs |
|---|---|---|---|---|
| 16 GB | 10.7 GiB | 8 of 22 | 3 | Mistral-Nemo-Instruct-2407, Q4_K_M |
| 24 GB | 16.0 GiB | 11 of 22 | 1 | Qwen2.5-14B-Instruct, Q6_K |
| 32 GB | 21.3 GiB | 13 of 22 | 3 | Qwen3-30B-A3B, Q4_K_M |
| 36 GB | 27.0 GiB | 16 of 22 | 0 | Qwen2.5-32B-Instruct, Q4_K_M |
| 48 GB | 36.0 GiB | 17 of 22 | 0 | Mixtral-8x7B-Instruct-v0.1, Q4_K_M |
| 64 GB | 48.0 GiB | 17 of 22 | 3 | Mixtral-8x7B-Instruct-v0.1, Q6_K |
| 128 GB | 96.0 GiB | 21 of 22 | 0 | GLM-4.5-Air, Q5_K_M |
Budget is the default share macOS gives the GPU: 67% up to 32 GB and 75% above (the rule and sources are on each tier page). Verdicts use the catalog's llama.cpp GGUF files, one sequence, fp16 KV cache and 8,192 tokens, over the 22 models in the Mac list. Mixture-of-experts models count at full file size. Sizes without a tier page (36, 256 and 512 GB) use the same rule. These are memory estimates, not runs on a Mac.
Data sources
- Apple MacBook Pro technical specifications — Chip, GPU core, bandwidth and memory options read 2026-10-18.
- Apple silicon unified memory and LLM sizing (LLMS-Explorer) — Quotes Apple's Metal Compute talk: 32 GB Mac gives the GPU 21 GB, 64 GB gives 48 GB. Newer 128 GB M4 Max logs show about 84%, so the share is not a constant.
- recommendedMaxWorkingSetSize (Apple Developer Forums) — Discussion of the default GPU working-set limit on Apple silicon.
- Model file sizes and architectures — catalog dataset 2026-10-02.1; GGUF bytes come from the Hugging Face repos listed on each model page