Summary
User reports Qwen3.8 Flash-Next IQ3_XXS on an RX 7900 XTX with 32GB system RAM in Strata, getting roughly 800 t/s prefill and 30-50 t/s decode on the first message.
Setup is the Strata AppImage WebUI with the IQ3_XXS quant, the model partly in system RAM given the 24GB card and 32GB RAM.
After the first reply, new chats hang on reading message, and an opencode call eventually stalled, freed memory and began reloading the model.
Compare this run
Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.
Qwen3.8 125B · 6B active at 4-bit by hardware
- 129.2 t/s · one run
- 105.5 t/s · 6 runs
- 57.2 t/s · 2 runs
- 55.0 t/s · one run
- 36.7 t/s · one run
- NVIDIA DGX Spark128 GB29.8 t/s · 2 runs
Bars are medians on one scale, 0 to 232.0 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.
Models most run on the AMD RX 7900 XTX
- Qwen3.8 27B4-bit40.0 t/s · 7 runs
- 142.8 t/s · one run
- Gemma 4 31B4-bit30.1 t/s · one run
- Gemma 4 8B16-bit58.0 t/s · one run
- 125.5 t/s · one run
Bars are medians on one scale, 0 to 142.8 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.
Everything reported on the AMD RX 7900 XTX →Every Qwen3.8 report →Estimate Qwen3.8 on this card →