Arao AI
Back to search results

Qwen3-4B · Q8_0

Start a discussion
AMD Radeon RX 907016GBllama.cpp v0.35L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B (Q8_0) on AMD Radeon RX 9070 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

73.3 tok/s

Decode

Decode speed

246.97 tok/s

Prefill

Prefill speed

0.63 s

TTFT

Time to first token

11.76 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. llama.cpp · Q2_K Decode 140.23 · Prefill 653.54 ·
  2. llama.cpp · Q8_0 (current)Decode 73.3 · Prefill 246.97 ·
  3. Strata · IQ4_XS Decode 168.75 · Prefill 844.33 ·

Core figures

Decode (avg)
73.3 tok/s
Prefill (avg)
246.97 tok/s
TTFT (avg)
0.63 s
VRAM (avg)
11.76 GB
MTP acceptance rate
—
TTFB
0.59 GB
Power draw
236.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B
Quantization
Q8_0
Framework
llama.cpp
Version
v0.35
Context length
4096 tokens
Batch size
256
GPU layers
33
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)
11.76 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.10
CUDA
N/A
Power draw
236.8 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.35 · Ubuntu 24.04 · CUDA N/A · 4096 ctx

    73.3 tok/s

    Decode

    246.97 tok/s

    Prefill

    0.63 s

    TTFT

    11.76 GB

    VRAM

    —

    MTP

    236.8 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=21 running model_id=54 at Q8_0