Can Qwen3 14B run on the RX 7900 XTX?
Yes. At 8K context the best fit is Q8_0, using about 16.6 GB of the 22.8 GB usable on the RX 7900 XTX. Estimated speed ceiling: ~61 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) | 6.5 GB Fits | 7.1 GB Fits | 10.8 GB Fits | 173 |
| 3-bit (Q3_K_M) | 8.0 GB Fits | 8.7 GB Fits | 12.4 GB Fits | 133 |
| 4-bit (Q4_K_M) • | 9.7 GB Fits | 10.3 GB Fits | 14.1 GB Fits | 107 |
| 5-bit (Q5_K_M) • | 11.1 GB Fits | 11.7 GB Fits | 15.5 GB Fits | 91 |
| 6-bit (Q6_K) • | 12.6 GB Fits | 13.2 GB Fits | 17.0 GB Fits | 79 |
| 8-bit (Q8_0) • | 15.9 GB Fits | 16.6 GB Fits | 20.3 GB Fits | 61 |
| 16-bit (F16/BF16) | 28.8 GB No | 29.4 GB No | 33.2 GB No | — |
• real GGUF file size from Qwen/Qwen3-14B-GGUF. Speed is a bandwidth ceiling (960 GB/s), not a benchmark. Methodology.
More
Qwen3 14B on every GPU and Mac · Every model that runs on the RX 7900 XTX · 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.