Can I run this LLM?
Can a MacBook Pro / Mac Studio M4 Max (128GB) run Qwen3 32B?
Qwen · Apache 2.0 · estimated for a 128.0 GB machine at 4K context.
Yes — it runs great.
Runs greatBest fit: Qwen3 32B at Q6_K · 26.9 GB weights · 12–18 tok/s on a MacBook Pro / Mac Studio M4 Max (128GB).
Arena Text Overall · style-controlled
1,347Q6_K untestedqwen3-32b · published configuration reference · Q6_K not tested
Arena Text Overall (style-controlled), exact published entry qwen3-32b, 2026-10-08: reference rating 1,346.9. Published confidence bounds 1,337.4–1,356.3. 3,926 votes. Published qwen3-32b configuration reference. Reasoning mode is not disclosed by the Arena dataset. Tested precision, runtime and sampling settings are not disclosed in this dataset. Selected Q6_K has not been measured by this Arena entry. No quantization quality adjustment is applied.
Snapshot published 2026-10-08 · snapshot imported 2026-10-11 UTC · validated last-good data · manual refresh
Arena leaderboard dataset · Arena / lmarena-ai, Arena Leaderboard Dataset (CC BY 4.0). Selected Text Overall style-controlled rows; field names adapted, ratings unchanged. · dataset CC BY 4.0 · revision e16f90232986
- Total memory at 4K context
- 28.8 GB
- Weights + KV cache + runtime overhead
- Estimated generation
- 12–18 tok/s
- Estimated first token
- ~24s
Every quantization on this machine
On small screens, each quant lists every metric below its name. On wider screens, scroll sideways for total memory, speed and fit. Keyboard: focus the table, then use the arrow keys. Quant names stay visible.
| Quant | Weights | Total memory | Speed | Fit |
|---|---|---|---|---|
| Q2_K | 12.3 GB | 14.2 GB | 24–36 tok/s | Runs great |
| Q3_K_M | 16.0 GB | 17.8 GB | 19–29 tok/s | Runs great |
| Q4_K_M | 19.8 GB | 21.6 GB | 16–24 tok/s | Runs great |
| Q5_K_M | 23.2 GB | 25.1 GB | 14–21 tok/s | Runs great |
| Q6_K | 26.9 GB | 28.8 GB | 12–18 tok/s | Runs great |
| Q8_0 | 34.8 GB | 36.7 GB | 10–15 tok/s | Tight / slow |
| FP16 | 65.5 GB | 67.4 GB | 5–8 tok/s | Tight / slow |
Ran Qwen3 32B on a MacBook Pro / Mac Studio M4 Max (128GB)? Add your real numbers →