No — not on this device
Qwen3 32B at Q4_K_M needs 21.0 GB against 18.0 GB usable, and the shortfall of 3.0 GB is more than 32 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.
Does not fit
8K context
Q4_K_M · 18.4 GB
Apache 2.0
Released Apr 2025
The classic 24 GB target, and still the strongest local translator under 70B. Qwen3.8 27B is smaller and better at everything else.
The VRAM budget
weights 18.4 GB
Weights 18.4 GB
KV cache @ 8K 2.00 GB
Runtime overhead 0.6 GB
Over budget 3.0 GB past 18.0 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 32.5 GB | 35.1 GB | — | ~1.7 | −0.1% ppl | 17.1 GB over |
| Q6_K | 25.0 GB | 27.6 GB | — | ~2.2 | −0.4% ppl | 9.6 GB over |
| Q5_K_M | 21.7 GB | 24.3 GB | — | ~2.6 | −0.8% ppl | 6.3 GB over |
| Q4_K_M | 18.4 GB | 21.0 GB | — | ~3.0 | −1.9% ppl | 3.0 GB over |
| Q3_K_M | 14.9 GB | 17.5 GB | 9K | 3.7 | −5.4% ppl | Fits |
| Q2_K | 12.8 GB | 15.4 GB | 18K | 4.4 | −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/Qwen3-32B-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
01Download is 18.4 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 18.0 GB of 24 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03If it falls back to CPU silently, drop the context first, then step down a quantisation.