llamaperf

Qwen3.8 125B (6B active) Flash-Next

on NVIDIA RTX 3090 · Strata · 39,800,000 ctx

Tone: mixedNVIDIA hardware
Nov 4, 2026
Throughput
41.0 t/s gen
Quant
IQ4
System RAM
96 GB

Summary

User reports Strata IQ4 Qwen3.8 Flash-Next decoding at 41 t/s on an RTX 3090 with a Xeon E5 and 96GB DDR4 ECC. Setup is Strata with IQ4 weights, used to edit a Qwen 0.6B model running fully on CPU in FP32, over a 39.8M-token run lasting 3h 12m. The edit steered the 0.6B model to answer a favourite-band question with Polyphia; the user calls the setup weird and questions whether models above 20B would benefit compared with traditional gradient training.

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

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 NVIDIA RTX 3090

Bars are medians on one scale, 0 to 111.7 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 NVIDIA RTX 3090 →Every Qwen3.8 report →Estimate Qwen3.8 on this card →