Can I run this LLM?
Can a MacBook Pro / Mac mini M4 Pro (48GB) run Qwen3 Coder Next 80B-A3B (MoE)?
Qwen · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Runs greatBest fit: Qwen3 Coder Next 80B-A3B (MoE) at Q2_K · 29.2 GB weights · 81–122 tok/s on a MacBook Pro / Mac mini M4 Pro (48GB).
Arena Text Overall · style-controlled
UnratedNo exact matchNo reviewed exact Arena match
No reviewed exact model/configuration match in the Arena Text Overall style-controlled snapshot. No family or editorial score is substituted. Local quantization quality is unmeasured.
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
- 30.1 GB
- Weights + KV cache + runtime overhead
- Estimated generation
- 81–122 tok/s
- Estimated first token
- ~4.3s
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 | 29.2 GB | 30.1 GB | 81–122 tok/s | Runs great |
| Q3_K_M | 38.3 GB | 39.2 GB | — not resident | Won't fit |
| Q4_K_M | 49.3 GB | 50.2 GB | — not resident | Won't fit |
| Q5_K_M | 59.2 GB | 60.1 GB | — not resident | Won't fit |
| Q6_K | 65.8 GB | 66.7 GB | — not resident | Won't fit |
| Q8_0 | 84.8 GB | 85.7 GB | — not resident | Won't fit |
| FP16 | 159.5 GB | 160.4 GB | — not resident | Won't fit |
Ran Qwen3 Coder Next 80B-A3B (MoE) on a MacBook Pro / Mac mini M4 Pro (48GB)? Add your real numbers →