llamaperf

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

on Unknown GPU · Strata

Tone: positive
Nov 8, 2026
Throughput
50.0 t/s gen
Quant
UD-Q4_K_XL (GGUF)

Use cases

coding

Summary

User reports Qwen3.8 Flash-Next at about 50 t/s while generating a C++ OpenGL town scene with walking pedestrians. Setup is Strata with an Unsloth UD-Q4_K_XL quant; the hardware is only referenced as the user's flair, so the GPU is not stated. The user notes it was not one-shot and kept a ledger of iterations, including a bug where pedestrian bodies rendered underground until corrected.

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.

Every Qwen3.8 report →