llamaperf

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

on NVIDIA RTX 3060 12GB · Strata · 128,000 ctx

Tone: positiveNVIDIA hardware
Nov 4, 2026
Throughput
33.0 t/s gen · 440.0 tokens/s prompt processing (prefill)Prompt processing is how fast the input is read, not how long you wait for the first word. How to measure time to first token.
Quant
IQ3_S(GSQ-RCO) (GGUF)
System RAM
64 GB
VRAM reported
12 GB

Use cases

coding

Summary

User reports Qwen3.8 Flash-Next at an average 33 t/s decode and 440 t/s prefill on an RTX 3060 12GB, from 86 requests in the Strata dashboard. Setup is Strata 0.2.9 with IQ3_S(GSQ-RCO) weights at 128k context, run through the DeepSeek harness with the billion-context plugin and reasoning effort at MAX. The one-shot 3D solar system build took 1h30m to finish; the user also ran Strata's auto-tuning five times and is unsure whether it helped.

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 3060 12GB

Bars are medians on one scale, 0 to 113.6 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 3060 12GB →Every Qwen3.8 report →Estimate Qwen3.8 on this card →