Arao AI
Back to search results

Llama-3.2-3B-Instruct · IQ3_S

Start a discussion
AMD Radeon RX 9070 XT16GBStrata v0.43L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (IQ3_S) on AMD Radeon RX 9070 XT with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

308.2 tok/s

Decode

Decode speed

1,415.95 tok/s

Prefill

Prefill speed

1.89 s

TTFT

Time to first token

6.26 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ3_XS Decode 319.75 · Prefill 1663.47 ·
  2. Strata · IQ3_S (current)Decode 308.2 · Prefill 1415.95 ·
  3. Strata · IQ4_XS Decode 311.94 · Prefill 1321.43 ·

Core figures

Decode (avg)
308.2 tok/s
Prefill (avg)
1,415.95 tok/s
TTFT (avg)
1.89 s
VRAM (avg)
6.26 GB
MTP acceptance rate
0.49
TTFB
2.47 GB
Power draw
245.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.2-3B-Instruct
Quantization
IQ3_S
Framework
Strata
Version
v0.43
Context length
2048 tokens
Batch size
256
GPU layers
8
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 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
6.26 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.11
CUDA
12.4
Power draw
245.5 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

    v0.43 · Ubuntu 24.04 · CUDA 12.4 · 2048 ctx

    308.2 tok/s

    Decode

    1,415.95 tok/s

    Prefill

    1.89 s

    TTFT

    6.26 GB

    VRAM

    0.49

    MTP

    245.5 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=16 running model_id=70 at IQ3_S