llamaperf

Qwen3.6 35B (3B active)

on AMD RX 9070 XT 16GB · ExLlamaV3 · 128,000 ctx

Tone: positiveAMD hardware
Nov 12, 2026
Throughput
71.6 t/s gen · 1246.0 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
EXL3 4.0 bpw (EXL3)
KV cache
Q8
System RAM
32 GB
VRAM reported
16 GB

Use cases

agenticlong-context

Summary

User benchmarks MoE expert offloading on an RX 9070 XT 16GB with 32GB DDR4, reporting Qwen3.6-35B-A3B at 71.6 t/s decode and 1246 t/s prefill at 128K context. Setup is ExLlamaV3 with EXL3 4.0 bpw and Q8 KV cache, DFlash2 with 2 drafts, experts offloaded to system RAM. Prefill drops from 1900 t/s at 16K to 700 t/s at 128K on the 35B models. Ornith 1.5 35B-A3B reached 57.3 t/s decode and 1168 t/s prefill at 128K, and Qwen3.8-Flash-Next Coder on Polystrata with IQ1_M reached 44.0 t/s decode and 1572 t/s prefill at 128K.

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.

Qwen3.6 35B · 3B active at 4-bit by hardware

Bars are medians on one scale, 0 to 215.1 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 RX 9070 XT 16GB

Bars are medians on one scale, 0 to 98.8 tokens/s. Press ▶ to watch text arrive at a row's speed.

Everything reported on the AMD RX 9070 XT 16GB →Every Qwen3.6 report →Estimate Qwen3.6 on this card →