RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

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

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)11.7 GB Fits12.1 GB Fits14.4 GB Fits23.4 GB Fits228
3-bit (Q3_K_M)15.0 GB Fits15.3 GB Fits17.6 GB Fits26.6 GB Fits175
4-bit (Q4_K_M) •18.4 GB Fits18.8 GB Fits21.0 GB Fits30.0 GB Fits140
5-bit (Q5_K_M)21.3 GB Fits21.7 GB Fits23.9 GB Fits32.9 GB Fits120
6-bit (Q6_K) •24.4 GB Fits24.8 GB Fits27.1 GB Fits36.1 GB Fits104
8-bit (Q8_0) •31.3 GB Fits31.7 GB Fits33.9 GB Fits42.9 GB Fits80
16-bit (F16/BF16)57.9 GB Fits58.3 GB Fits60.6 GB Fits69.6 GB Fits43

• 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

"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.