Can I Run Qwen 3 32B on Apple M2 Ultra?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 12 lipca 2026
Yes. Qwen 3 32B needs 22.8 GB at 8K context (19.8 GB weights + 3 GB KV cache/overhead) at Q4_K_M and the Apple M2 Ultra has 144 GB usable, leaving about 121.2 GB of headroom, at roughly 20 tok/s (estimated) with room for up to 64K of context.
See what else this hardware can run →
The numbers
| Model | Qwen 3 32B |
| Parameters | 32B |
| Quantization | Q4_K_M |
| VRAM needed (8K context) | 22.8 GB |
| Apple M2 Ultra usable memory | 144 GB |
| Verdict | Runs |
| Max context | 64K |
| Estimated speed | ~20 tok/s |
Qwen 3 32B on the Apple M2 Ultra: VRAM by quantization
| Quant | VRAM needed | Fits 192 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 68.5 GB | ✓ Yes | 64K | — |
| Q8_0 | 37.8 GB | ✓ Yes | 64K | Build for this |
| Q6_K | 29.8 GB | ✓ Yes | 64K | — |
| Q5_K_M | 26.2 GB | ✓ Yes | 64K | Build for this |
| Q4_K_M | 22.8 GB | ✓ Yes | 64K | Build for this |
| Q3_K_M | 16.9 GB | ✓ Yes | 64K | — |
| Q2_K | 13.7 GB | ✓ Yes | 64K | — |
Assumes an 8K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 192 GB of unified memory. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the Apple M2 Ultra: 8K 22.8 GB · 32K 29.2 GB · 125K 54.2 GB. Every window this model publishes still fits 192 GB.
What to do next
Nothing to change — run it at Q4_K_M. If you want more capability, check whether the next size up also fits.
No compatible GPU? Qwen 3 32B on 32 GB of system RAM, CPU only: runs comfortably.
Running Qwen 3 32B on this card:
Qwen 3 32B needs ~23 GB but this GPU has 192 GB. Rent a RTX 4090 (24 GB)-class GPU by the hour instead of buying one:
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
Other Qwen 3 sizes on the Apple M2 Ultra
- Qwen 3 235B-A22B (MoE) — runs at a lower quant (144.3 GB)
- Qwen 3 30B-A3B (MoE) — runs (20 GB)
- Qwen 3 14B — runs (11.1 GB)
- Qwen 3 8B — runs (7 GB)
Qwen 3 32B on nearby hardware
- NVIDIA L40S (48 GB) — runs
All Qwen 3 sizes on the Apple M2 Ultra | Qwen 3 32B model page | Apple M2 Ultra GPU page | VRAM calculator | Check your hardware