Arao AI
Back to search results

Qwen3-8B · Q2_K

Start a discussion
AMD Radeon RX 7800 XT16GBllama.cpp v0.39L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (Q2_K) on AMD Radeon RX 7800 XT with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

105.63 tok/s

Decode

Decode speed

545.14 tok/s

Prefill

Prefill speed

2.36 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

5 days ago

Last verified

Performance

  1. llama.cpp · Q2_K (current)Decode 105.63 · Prefill 545.14 ·
  2. Ollama · IQ3_XS Decode 100 · Prefill 339.13 ·

Core figures

Decode (avg)
105.63 tok/s
Prefill (avg)
545.14 tok/s
TTFT (avg)
2.36 s
VRAM (avg)
11.34 GB
MTP acceptance rate
—
TTFB
0.85 GB
Power draw
255.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
Q2_K
Framework
llama.cpp
Version
v0.39
Context length
8192 tokens
Batch size
256
GPU layers
33
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 7800 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
11.34 GB
OS
Ubuntu 24.04
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
255.7 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

    v0.39 · Ubuntu 24.04 · CUDA N/A · 8192 ctx

    105.63 tok/s

    Decode

    545.14 tok/s

    Prefill

    2.36 s

    TTFT

    11.34 GB

    VRAM

    —

    MTP

    255.7 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=31 running model_id=53 at Q2_K