llamaperf

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

on AMD Strix Halo 128GB · llama.cpp · 4,096 ctx

Tone: positiveAMD hardware
Nov 3, 2026
Throughput
21.0 t/s gen · 520.0 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
UD-Q4_K_XL (GGUF)
System RAM
128 GB

Use cases

codingagenticlong-context

Summary

User reports Qwen3.8-Flash-Next at about 21 t/s decode at 4K context and about 14 t/s at 128K on an AMD Strix Halo 128GB, with prefill 520 t/s falling to 230 t/s. Setup is llama.cpp (llama-server) on ROCm with UD-Q4_K_XL, 262K context and the MTP draft head, driven headless by Claude Code. MTP gives about 1.5x up to 64K and becomes a loss past about 100K. The review ran 53 turns over 41 minutes with context growing to about 110K tokens; the user calls it an anecdote, not a benchmark.

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 AMD Strix Halo 128GB

Bars are medians on one scale, 0 to 77.0 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 AMD Strix Halo 128GB →Every Qwen3.8 report →Estimate Qwen3.8 on this card →