Arao AI
Back to search results

Llama-3.1-8B-Instruct · Q3_K_M

Start a discussion
AMD Radeon RX 907016GBvLLM v0.21L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (Q3_K_M) on AMD Radeon RX 9070 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

141.43 tok/s

Decode

Decode speed

703.16 tok/s

Prefill

Prefill speed

1.66 s

TTFT

Time to first token

13.52 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ1_S Decode 209.03 · Prefill 1072.51 ·
  2. vLLM · Q3_K_M (current)Decode 141.43 · Prefill 703.16 ·
  3. Strata · Q3_K_L Decode 194.02 · Prefill 811.8 ·

Core figures

Decode (avg)
141.43 tok/s
Prefill (avg)
703.16 tok/s
TTFT (avg)
1.66 s
VRAM (avg)
13.52 GB
MTP acceptance rate
—
TTFB
1.13 GB
Power draw
214.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
Q3_K_M
Framework
vLLM
Version
v0.21
Context length
8192 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 9070
Nominal VRAM
16 GB
Measured VRAM (avg)
13.52 GB
OS
Ubuntu 22.04
Driver
amdgpu-pro 24.20
CUDA
12.8
Power draw
214.2 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

    v0.21 · Ubuntu 22.04 · CUDA 12.8 · 8192 ctx

    141.43 tok/s

    Decode

    703.16 tok/s

    Prefill

    1.66 s

    TTFT

    13.52 GB

    VRAM

    —

    MTP

    214.2 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=21 running model_id=68 at Q3_K_M