Apple M4 Pro, 48 GB · Qwen3 32B · Q4_K_M
Yes. Apple M4 Pro, 48 GB runs Qwen3 32B at Q4_K_M with room left at 8,192 tokens, roughly 7–11 tokens per second.
| Piece | Value | Note |
|---|---|---|
| Weights | 18.4 GiB | Qwen3-32B-Q4_K_M.gguf |
| KV cache | 2.00 GiB | 8,192 tokens |
| Engine overhead | 0.50 GiB | Flat 0.5 GiB allowance |
| 5% headroom | 1.05 GiB | On the sum above |
| Total | 22.0 GiB | Fits |
| Fast memory | 36.0 GiB | After OS reserve |
| Speed | 7–11 tok/s | Dense bandwidth range |
ollama run qwen3:32b
Apple M4 Pro, 48 GB · Qwen3 32B ·GGUF file · Methodology
FAQ
How was this fit calculated?
Weights 18.4 GiB, KV cache 2.00 GiB at 8,192 tokens, engine overhead 0.50 GiB, then 5% headroom, for 22.0 GiB. Fast memory available is 36.0 GiB.
What if I change the quant or the context?
This page is Q4_K_M at 8,192 tokens. A smaller quant or a shorter context lowers the total. The homepage calculator changes both without a new page.
Can I trust the tokens per second?
The range 7–11 tok/s is a bandwidth roofline, 55% to 80% efficient. This dense model reads the whole weight file each token. Measure your own box before you buy around it.
What do I type?
ollama run qwen3:32b
Is Apple M4 Pro, 48 GB assumed to have extra RAM?
No separate RAM pool. The chip's unified memory is the whole budget, minus the OS reserve described on the methodology page.