Arao AI
Back to search results

Qwen3.8-9B · Q8_0

Start a discussion
AMD Radeon RX 7900 XTX24GBvLLM v0.42L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q8_0) on AMD Radeon RX 7900 XTX with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

60.74 tok/s

Decode

Decode speed

270.33 tok/s

Prefill

Prefill speed

1.16 s

TTFT

Time to first token

22.8 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ2_M Decode 116.92 · Prefill 403.5 ·
  2. llama.cpp · Q4_K_S Decode 92.32 · Prefill 411.04 ·
  3. vLLM · Q8_0 (current)Decode 60.74 · Prefill 270.33 ·

Core figures

Decode (avg)
60.74 tok/s
Prefill (avg)
270.33 tok/s
TTFT (avg)
1.16 s
VRAM (avg)
22.8 GB
MTP acceptance rate
—
TTFB
0.49 GB
Power draw
457.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q8_0
Framework
vLLM
Version
v0.42
Context length
8192 tokens
Batch size
8
GPU layers
999
Flash Attention
Off

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
AMD Radeon RX 7900 XTX
Nominal VRAM
24 GB
Measured VRAM (avg)
22.8 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.6
Power draw
457.1 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-10

    v0.42 · Ubuntu 22.04 · CUDA 12.6 · 8192 ctx

    60.74 tok/s

    Decode

    270.33 tok/s

    Prefill

    1.16 s

    TTFT

    22.8 GB

    VRAM

    —

    MTP

    457.1 W

    Power draw

    L2 batch seed 2026-10-10: vLLM on hw_id=11 running model_id=52 at Q8_0