Arao AI
Back to search results

Qwen3-8B · Q8_0

Start a discussion
AMD Radeon RX 7900 XTX24GBStrata v0.46L2 Cross-framework verified

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

88.6 tok/s

Decode

Decode speed

455.19 tok/s

Prefill

Prefill speed

1.19 s

TTFT

Time to first token

21.42 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ2_M Decode 141.39 · Prefill 740.19 ·
  2. Ollama · Q5_K_S Decode 83.18 · Prefill 356.29 ·
  3. Strata · Q8_0 (current)Decode 88.6 · Prefill 455.19 ·

Core figures

Decode (avg)
88.6 tok/s
Prefill (avg)
455.19 tok/s
TTFT (avg)
1.19 s
VRAM (avg)
21.42 GB
MTP acceptance rate
0.61
TTFB
0.71 GB
Power draw
341.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
Q8_0
Framework
Strata
Version
v0.46
Context length
2048 tokens
Batch size
512
GPU layers
5
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)
21.42 GB
OS
Windows 11 23H2
Driver
560.94
CUDA
12.6
Power draw
341.4 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

    v0.46 · Windows 11 23H2 · CUDA 12.6 · 2048 ctx

    88.6 tok/s

    Decode

    455.19 tok/s

    Prefill

    1.19 s

    TTFT

    21.42 GB

    VRAM

    0.61

    MTP

    341.4 W

    Power draw

    L2 batch seed 2026-10-10: Strata on hw_id=11 running model_id=53 at Q8_0