Can Qwen3 Coder 30B A3B Instruct run on the Ryzen AI Max+ 395 128GB?
Yes. At 8K context the best fit is F16, using about 58.3 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~43 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 11.7 GB Fits | 12.1 GB Fits | 14.4 GB Fits | 23.4 GB Fits | 228 |
| 3-bit (Q3_K_M) | 15.0 GB Fits | 15.3 GB Fits | 17.6 GB Fits | 26.6 GB Fits | 175 |
| 4-bit (Q4_K_M) • | 18.4 GB Fits | 18.8 GB Fits | 21.0 GB Fits | 30.0 GB Fits | 140 |
| 5-bit (Q5_K_M) | 21.3 GB Fits | 21.7 GB Fits | 23.9 GB Fits | 32.9 GB Fits | 120 |
| 6-bit (Q6_K) • | 24.4 GB Fits | 24.8 GB Fits | 27.1 GB Fits | 36.1 GB Fits | 104 |
| 8-bit (Q8_0) • | 31.3 GB Fits | 31.7 GB Fits | 33.9 GB Fits | 42.9 GB Fits | 80 |
| 16-bit (F16/BF16) | 57.9 GB Fits | 58.3 GB Fits | 60.6 GB Fits | 69.6 GB Fits | 43 |
• real GGUF file size from lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-GGUF. Speed is a bandwidth ceiling (256 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs Qwen3 Coder 30B A3B Instruct: RX 7900 XTX (24 GB, launch MSRP $999) at Q4_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the Ryzen AI Max+ 395 128GB: gpt-oss 120B (117B, MoE) at F16, about 61.9 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 Coder 30B A3B Instruct on every GPU and Mac · Every model that runs on the Ryzen AI Max+ 395 128GB · Other models that fit 64 GB VRAM · 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-Coder-30B-A3B-Instruct), AMD specs. Model data last checked 2026-11-18; refreshed hourly.