Arao AI
Back to search results

Qwen3-8B · Q2_K

Start a discussion
AMD Radeon RX 7900 XTX24GBvLLM v0.29L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (Q2_K) on AMD Radeon RX 7900 XTX with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

108.21 tok/s

Decode

Decode speed

417.97 tok/s

Prefill

Prefill speed

1.3 s

TTFT

Time to first token

11.34 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. llama.cpp · Q5_K_S Decode 73.41 · Prefill 264.95 ·
  2. vLLM · IQ2_M Decode 127.88 · Prefill 585.23 ·
  3. vLLM · Q2_K (current)Decode 108.21 · Prefill 417.97 ·
  4. Ollama · IQ3_XS Decode 90.61 · Prefill 409.37 ·
  5. Strata · IQ2_M Decode 148.41 · Prefill 586.66 ·
  6. Ollama · Q5_K_S Decode 83.18 · Prefill 356.29 ·
  7. Strata · Q8_0 Decode 88.6 · Prefill 455.19 ·

Core figures

Decode (avg)
108.21 tok/s
Prefill (avg)
417.97 tok/s
TTFT (avg)
1.3 s
VRAM (avg)
11.34 GB
MTP acceptance rate
—
TTFB
0.87 GB
Power draw
269.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
Q2_K
Framework
vLLM
Version
v0.29
Context length
16384 tokens
Batch size
16
GPU layers
999
Flash Attention
On

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)
11.34 GB
OS
Ubuntu 24.04
Driver
amdgpu-pro 24.20
CUDA
12.8
Power draw
269.9 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.29 · Ubuntu 24.04 · CUDA 12.8 · 16384 ctx

    108.21 tok/s

    Decode

    417.97 tok/s

    Prefill

    1.3 s

    TTFT

    11.34 GB

    VRAM

    —

    MTP

    269.9 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=11 running model_id=53 at Q2_K