vLLM on the AMD RX 7900 XTX
On the AMD RX 7900 XTX, vLLM runs Gemma 4 8B at 16-bit at a median 58.0 tokens per second for generation, from 1 plain run (context not stated).
Speed by model on the AMD RX 7900 XTX
Plain runs only: one device, one request, no speculative decoding, the whole model in memory. Each row is one model size at one bit class, with the other engines' plain runs of the same model on this card beside it. Context length and build still differ between runs, and each side shows its own.
| Model | vLLM | Other engines |
|---|---|---|
| Gemma 4 8B 16-bit | 58.0 t/sone report, context not stated | no other engine reported |
3 vLLM reports on the AMD RX 7900 XTX
Newest first. A run on several cards, with speculative decoding, with part of the model in system RAM or with batched requests says so, since each describes a different setup.
- Qwen3.8 27B · BF1650.0 t/s(6 cards)
- Model not identified100.0 t/s(4 cards)
- Gemma 4 8B · FP1658.0 t/s
Frequently asked
How fast is vLLM on the AMD RX 7900 XTX?
On the AMD RX 7900 XTX, vLLM runs Gemma 4 8B at 16-bit at a median 58.0 tokens per second for generation, from 1 plain run (context not stated).