Arao AI
Back to search results

Llama-3.1-8B-Instruct · Q4_K_M

Start a discussion
AMD Radeon RX 7900 XTX24GBvLLM v0.32L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (Q4_K_M) on AMD Radeon RX 7900 XTX with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

87.13 tok/s

Decode

Decode speed

426.78 tok/s

Prefill

Prefill speed

1.46 s

TTFT

Time to first token

15.88 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. llama.cpp · Q3_K_S Decode 102.17 · Prefill 424.1 ·
  2. llama.cpp · Q4_K_M Decode 83.47 · Prefill 411.3 ·
  3. vLLM · Q3_K_M Decode 114.54 · Prefill 374.54 ·
  4. vLLM · Q4_K_M (current)Decode 87.13 · Prefill 426.78 ·
  5. vLLM · IQ4_XS Decode 91.85 · Prefill 357.41 ·
  6. Strata · IQ4_XS Decode 138.01 · Prefill 527.22 ·

Core figures

Decode (avg)
87.13 tok/s
Prefill (avg)
426.78 tok/s
TTFT (avg)
1.46 s
VRAM (avg)
15.88 GB
MTP acceptance rate
—
TTFB
0.7 GB
Power draw
200.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
Q4_K_M
Framework
vLLM
Version
v0.32
Context length
32768 tokens
Batch size
32
GPU layers
999
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)
15.88 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.11
CUDA
12.8
Power draw
200.4 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.32 · Ubuntu 24.04 · CUDA 12.8 · 32768 ctx

    87.13 tok/s

    Decode

    426.78 tok/s

    Prefill

    1.46 s

    TTFT

    15.88 GB

    VRAM

    —

    MTP

    200.4 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=11 running model_id=68 at Q4_K_M