llamaperf

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

on NVIDIA RTX 4070 Super · Strata

Tone: mixedNVIDIA hardware
Nov 4, 2026
Throughput
60-70 t/s gen
Quant
IQ3_XXS (GGUF)
System RAM
64 GB
VRAM reported
12 GB

Use cases

coding

Summary

User compares a local Qwen3.8 Flash-Next IQ3_XXS run in Strata against Claude on a coding task, generating a playable first-person motorcycle browser game in HTML. The local run used an RTX 4070 Super 12GB plus 64GB DDR5, with almost 50GB of RAM in use and only about 7GB left for other tasks. Thinking was capped at 16K tokens because the model otherwise consumed nearly 64K of context. Decode was around 60-70 tok/s with peaks over 100 tok/s, and the task took 396 s plus 274 s over two requests, about 11 minutes. The user found the result not really playable and concludes local setups are not worthwhile for coding on personal PCs.

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.

Everything reported on the NVIDIA RTX 4070 Super →Every Qwen3.8 report →Estimate Qwen3.8 on this card →