Arao AI
Back to search results

Llama-3.1-8B-Instruct · Q2_K

Start a discussion
AMD Ryzen AI Max+ 395128GBvLLM v0.26L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (Q2_K) on AMD Ryzen AI Max+ 395 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

51.17 tok/s

Decode

Decode speed

219.96 tok/s

Prefill

Prefill speed

1.72 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

17 days ago

Last verified

Performance

  1. llama.cpp · IQ3_XS Decode 45.88 · Prefill 214.9 ·
  2. vLLM · Q2_K (current)Decode 51.17 · Prefill 219.96 ·

Core figures

Decode (avg)
51.17 tok/s
Prefill (avg)
219.96 tok/s
TTFT (avg)
1.72 s
VRAM (avg)
11.34 GB
MTP acceptance rate
—
TTFB
0.41 GB
Power draw
61 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
Q2_K
Framework
vLLM
Version
v0.26
Context length
8192 tokens
Batch size
8
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 Ryzen AI Max+ 395
Nominal VRAM
128 GB
Measured VRAM (avg)
11.34 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.12
CUDA
12.4
Power draw
61 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

    v0.26 · Ubuntu 24.04 · CUDA 12.4 · 8192 ctx

    51.17 tok/s

    Decode

    219.96 tok/s

    Prefill

    1.72 s

    TTFT

    11.34 GB

    VRAM

    —

    MTP

    61 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=24 running model_id=68 at Q2_K