Arao AI
Back to search results

Llama-3-8B-Instruct · Q5_K_S

Start a discussion
AMD Radeon RX 7900 XTX24GBOllama v0.50L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q5_K_S) on AMD Radeon RX 7900 XTX with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

74.62 tok/s

Decode

Decode speed

395.14 tok/s

Prefill

Prefill speed

0.18 s

TTFT

Time to first token

17.22 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · Q6_K Decode 72.29 · Prefill 325.63 ·
  2. Ollama · IQ4_XS Decode 87.11 · Prefill 460.37 ·
  3. Ollama · Q5_K_S (current)Decode 74.62 · Prefill 395.14 ·

Core figures

Decode (avg)
74.62 tok/s
Prefill (avg)
395.14 tok/s
TTFT (avg)
0.18 s
VRAM (avg)
17.22 GB
MTP acceptance rate
—
TTFB
0.6 GB
Power draw
258.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q5_K_S
Framework
Ollama
Version
v0.50
Context length
4096 tokens
Batch size
512
GPU layers
99
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 7900 XTX
Nominal VRAM
24 GB
Measured VRAM (avg)
17.22 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.11
CUDA
12.8
Power draw
258.5 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

    v0.50 · Ubuntu 24.04 · CUDA 12.8 · 4096 ctx

    74.62 tok/s

    Decode

    395.14 tok/s

    Prefill

    0.18 s

    TTFT

    17.22 GB

    VRAM

    —

    MTP

    258.5 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=11 running model_id=69 at Q5_K_S