Yes — with 5.1 GB to spare
Granite 4.1 30B at Q4_K_M fits your M2 Pro · 32 GB entirely in unified memory at 8K context, at an estimated 6.9 tokens per second. Past 28K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
Fully in unified memory
8K context
Q4_K_M · 16.3 GB
Apache 2.0
Released 29 Apr 2026
The largest Granite. Dense 29B at Q4 is a comfortable 24 GB fit.
The VRAM budget
weights 16.3 GB
Weights 16.3 GB
KV cache @ 8K 2.00 GB
Runtime overhead 0.6 GB
Free 5.1 GB of 24.0 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 28.6 GB | 31.2 GB | — | ~3.9 | −0.1% ppl | 7.2 GB over |
| Q6_K | 22.1 GB | 24.7 GB | 5K | ~5.1 | −0.4% ppl | 0.7 GB over |
| Q5_K_M | 19.1 GB | 21.7 GB | 17K | 5.9 | −0.8% ppl | Long context |
| Q4_K_M | 16.3 GB | 18.9 GB | 28K | 6.9 | −1.9% ppl | Recommended |
| Q3_K_M | 13.2 GB | 15.8 GB | 40K | 8.5 | −5.4% ppl | Long context |
| Q2_K | 11.3 GB | 13.9 GB | 48K | 9.9 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.
How to run it
$ pip install mlx-lm $ mlx_lm.generate --model mlx-community/granite-4.1-30b-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
01Download is 16.3 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02macOS caps what the GPU may wire down at about 24.0 GB of 32 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03There is room to go to 28K context on this card.