Arao AI
Back to search results

Qwen3-4B · Q2_K

Start a discussion
AMD Radeon RX 9070 GRE12GBllama.cpp v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B (Q2_K) on AMD Radeon RX 9070 GRE with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

124.6 tok/s

Decode

Decode speed

437.09 tok/s

Prefill

Prefill speed

2.17 s

TTFT

Time to first token

6.72 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 (current)Decode 124.6 · Prefill 437.09 ·

Core figures

Decode (avg)
124.6 tok/s
Prefill (avg)
437.09 tok/s
TTFT (avg)
2.17 s
VRAM (avg)
6.72 GB
MTP acceptance rate
—
TTFB
1 GB
Power draw
252 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B
Quantization
Q2_K
Framework
llama.cpp
Version
v0.46
Context length
16384 tokens
Batch size
512
GPU layers
99
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 9070 GRE
Nominal VRAM
12 GB
Measured VRAM (avg)
6.72 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.11
CUDA
N/A
Power draw
252 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

    v0.46 · Ubuntu 24.04 · CUDA N/A · 16384 ctx

    124.6 tok/s

    Decode

    437.09 tok/s

    Prefill

    2.17 s

    TTFT

    6.72 GB

    VRAM

    —

    MTP

    252 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=32 running model_id=54 at Q2_K