RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Qwen3 Coder 30B A3B Instruct run on the RX 7900 XT?

Yes. At 8K context the best fit is Q3_K_M, using about 15.1 GB of the 19.0 GB usable on the RX 7900 XT. Estimated speed ceiling: ~553 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •11.6 GB Fits11.9 GB Fits14.2 GB Fits23.2 GB No723
3-bit (Q3_K_M) •14.8 GB Fits15.1 GB Fits17.4 GB Tight26.4 GB No553
4-bit (Q4_K_M) •18.3 GB Tight18.7 GB Tight21.0 GB No30.0 GB No439
5-bit (Q5_K_M) •21.3 GB No21.7 GB No23.9 GB No32.9 GB No—
6-bit (Q6_K) •24.4 GB No24.8 GB No27.1 GB No36.1 GB No—
8-bit (Q8_0) •31.3 GB No31.7 GB No33.9 GB No42.9 GB No—
16-bit (F16/BF16) •58.0 GB No58.3 GB No60.6 GB No69.6 GB No—

• real GGUF file size from unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF. Speed is a bandwidth ceiling (800 GB/s), not a benchmark. Methodology.

More

Qwen3 Coder 30B A3B Instruct on every GPU and Mac · Every model that runs on the RX 7900 XT · Other models that fit 24 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (Qwen/Qwen3-Coder-30B-A3B-Instruct), AMD specs. Data as of 2026-11-17.