llamaperf

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

on NVIDIA RTX 5060 Ti 16GB · Strata · 128,000 ctx

Tone: positiveNVIDIA hardware
Nov 5, 2026
Throughput
49-69 t/s gen · 1600.0 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)
KV cache
Int-8
System RAM
80 GB
VRAM reported
16 GB

Summary

User reports Qwen3.8 Flash-Next decoding at 49-69 tk/s with 1600 tk/s prefill on an RTX 5060 Ti 16GB, alongside an R9 5950X and 80 GB of RAM. Setup is Strata with an IQ3_S GSQ RCO quant, Int-8 KV cache and a 128k context window. Decode is given only as a range, so no single generation figure is recorded. The user is new to the setup and asks for tips.

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 5060 Ti 16GB

Bars are medians on one scale, 0 to 95.2 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 5060 Ti 16GB →Every Qwen3.8 report →Estimate Qwen3.8 on this card →