RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Qwen3 14B run on the RX 7900 XT?

Yes. At 8K context the best fit is Q8_0, using about 16.6 GB of the 19.0 GB usable on the RX 7900 XT. Estimated speed ceiling: ~51 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)6.5 GB Fits7.1 GB Fits10.8 GB Fits144
3-bit (Q3_K_M)8.0 GB Fits8.7 GB Fits12.4 GB Fits111
4-bit (Q4_K_M) •9.7 GB Fits10.3 GB Fits14.1 GB Fits89
5-bit (Q5_K_M) •11.1 GB Fits11.7 GB Fits15.5 GB Fits76
6-bit (Q6_K) •12.6 GB Fits13.2 GB Fits17.0 GB Fits66
8-bit (Q8_0) •15.9 GB Fits16.6 GB Fits20.3 GB No51
16-bit (F16/BF16)28.8 GB No29.4 GB No33.2 GB No—

• real GGUF file size from Qwen/Qwen3-14B-GGUF. Speed is a bandwidth ceiling (800 GB/s), not a benchmark. Methodology.

More

Qwen3 14B 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/Qwen3-14B), AMD specs. Data as of 2026-11-17.