Arao AI
Back to search results

Llama-3-8B-Instruct · Q5_K_S

Start a discussion
AMD Radeon RX 9070 XT16GBllama.cpp v0.52L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q5_K_S) on AMD Radeon RX 9070 XT with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

108.87 tok/s

Decode

Decode speed

379.25 tok/s

Prefill

Prefill speed

0.6 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 · Q5_K_S (current)Decode 108.87 · Prefill 379.25 ·
  2. Ollama · Q2_K Decode 175.64 · Prefill 836.53 ·

Core figures

Decode (avg)
108.87 tok/s
Prefill (avg)
379.25 tok/s
TTFT (avg)
0.6 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
0.87 GB
Power draw
256.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q5_K_S
Framework
llama.cpp
Version
v0.52
Context length
2048 tokens
Batch size
512
GPU layers
28
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 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
15.2 GB
OS
Ubuntu 22.04
Driver
amdgpu-pro 24.20
CUDA
12.8
Power draw
256.5 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

    v0.52 · Ubuntu 22.04 · CUDA 12.8 · 2048 ctx

    108.87 tok/s

    Decode

    379.25 tok/s

    Prefill

    0.6 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    256.5 W

    Power draw

    L2 batch seed 2026-10-18: llama.cpp on hw_id=16 running model_id=69 at Q5_K_S