Arao AI
Back to search results

Llama-3.1-8B-Instruct · IQ1_S

Start a discussion
AMD Radeon RX 907016GBvLLM v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (IQ1_S) on AMD Radeon RX 9070 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

209.03 tok/s

Decode

Decode speed

1,072.51 tok/s

Prefill

Prefill speed

0.88 s

TTFT

Time to first token

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

Core figures

Decode (avg)
209.03 tok/s
Prefill (avg)
1,072.51 tok/s
TTFT (avg)
0.88 s
VRAM (avg)
9.16 GB
MTP acceptance rate
—
TTFB
1.67 GB
Power draw
219.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
IQ1_S
Framework
vLLM
Version
v0.30
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 9070
Nominal VRAM
16 GB
Measured VRAM (avg)
9.16 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.12
CUDA
12.6
Power draw
219.3 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

    v0.30 · Ubuntu 22.04 · CUDA 12.6 · 32768 ctx

    209.03 tok/s

    Decode

    1,072.51 tok/s

    Prefill

    0.88 s

    TTFT

    9.16 GB

    VRAM

    —

    MTP

    219.3 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=21 running model_id=68 at IQ1_S