Arao AI
Back to search results

Llama-3-8B-Instruct · Q2_K

Start a discussion
AMD Radeon RX 9070 XT16GBOllama v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q2_K) on AMD Radeon RX 9070 XT with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

175.64 tok/s

Decode

Decode speed

836.53 tok/s

Prefill

Prefill speed

0.91 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

Today

Last verified

Performance

  1. llama.cpp · Q5_K_S Decode 108.87 · Prefill 379.25 ·
  2. Ollama · Q2_K (current)Decode 175.64 · Prefill 836.53 ·

Core figures

Decode (avg)
175.64 tok/s
Prefill (avg)
836.53 tok/s
TTFT (avg)
0.91 s
VRAM (avg)
11.34 GB
MTP acceptance rate
—
TTFB
1.41 GB
Power draw
227 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q2_K
Framework
Ollama
Version
v0.48
Context length
32768 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 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
11.34 GB
OS
Windows 11 23H2
Driver
amdgpu 6.12
CUDA
12.6
Power draw
227 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

    v0.48 · Windows 11 23H2 · CUDA 12.6 · 32768 ctx

    175.64 tok/s

    Decode

    836.53 tok/s

    Prefill

    0.91 s

    TTFT

    11.34 GB

    VRAM

    —

    MTP

    227 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=16 running model_id=69 at Q2_K