Can Qwen3.8 2.4T A95B run on the Mac M3 Pro 36GB?
No. Even at 2-bit with 8K context, Qwen3.8 2.4T A95B needs about 856 GB, more than the 24.1 GB usable on the Mac M3 Pro 36GB.
On this machine the GPU and CPU share one memory pool, so CPU offload does not add room. A smaller quant, a shorter context or more memory are the options.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 856 GB No | 856 GB No | 858 GB No | 867 GB No | — |
| 3-bit (Q3_K_M) | 1115 GB No | 1115 GB No | 1117 GB No | 1126 GB No | — |
| 4-bit (Q4_K_M) | 1394 GB No | 1394 GB No | 1396 GB No | 1405 GB No | — |
| 5-bit (Q5_K_M) | 1624 GB No | 1625 GB No | 1627 GB No | 1636 GB No | — |
| 6-bit (Q6_K) | 1869 GB No | 1870 GB No | 1872 GB No | 1880 GB No | — |
| 8-bit (Q8_0) • | 2423 GB No | 2423 GB No | 2425 GB No | 2434 GB No | — |
| 16-bit (F16/BF16) • | 4558 GB No | 4559 GB No | 4561 GB No | 4569 GB No | — |
• real GGUF file size from unsloth/Qwen3.8-2.4T-A95B-GGUF. Speed is a bandwidth ceiling (150 GB/s), not a benchmark. Methodology.
What fits instead
- Nothing we list runs Qwen3.8 2.4T A95B fully in memory at 8K context. It needs a multi-GPU server.
- Largest popular model that fits the Mac M3 Pro 36GB: Qwen3 32B (33B) at Q4_K_M, about 21.1 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
Qwen3.8 2.4T A95B on every GPU and Mac · Every model that runs on the Mac M3 Pro 36GB · Apple Silicon guide · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (Qwen/Qwen3.8-2.4T-A95B), Apple specs. Model data last checked 2026-11-18; refreshed hourly.