Arao AI
Back to search results

Qwen3-8B · Q4_K_S

Start a discussion
AMD Radeon RX 907016GBStrata v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (Q4_K_S) on AMD Radeon RX 9070 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

150.11 tok/s

Decode

Decode speed

526.56 tok/s

Prefill

Prefill speed

0.1 s

TTFT

Time to first token

15.2 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · Q3_K_L Decode 112.13 · Prefill 574.57 ·
  2. llama.cpp · Q5_K_M Decode 84.7 · Prefill 430.21 ·
  3. Strata · Q4_K_S (current)Decode 150.11 · Prefill 526.56 ·
  4. Strata · Q3_K_L Decode 126.35 · Prefill 621.6 ·
  5. Strata · Q3_K_S Decode 136.8 · Prefill 667.03 ·

Core figures

Decode (avg)
150.11 tok/s
Prefill (avg)
526.56 tok/s
TTFT (avg)
0.1 s
VRAM (avg)
15.2 GB
MTP acceptance rate
0.74
TTFB
1.2 GB
Power draw
226.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
Q4_K_S
Framework
Strata
Version
v0.46
Context length
32768 tokens
Batch size
1024
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 9070
Nominal VRAM
16 GB
Measured VRAM (avg)
15.2 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.12
CUDA
12.4
Power draw
226.8 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.46 · Ubuntu 24.04 · CUDA 12.4 · 32768 ctx

    150.11 tok/s

    Decode

    526.56 tok/s

    Prefill

    0.1 s

    TTFT

    15.2 GB

    VRAM

    0.74

    MTP

    226.8 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=21 running model_id=53 at Q4_K_S