Arao AI
Back to search results

Llama-3.2-3B-Instruct · IQ4_XS

Start a discussion
AMD Radeon RX 9070 XT16GBStrata v0.29L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (IQ4_XS) on AMD Radeon RX 9070 XT with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

311.94 tok/s

Decode

Decode speed

1,321.43 tok/s

Prefill

Prefill speed

0.8 s

TTFT

Time to first token

6.76 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 Decode 308.2 · Prefill 1415.95 ·
  3. Strata · IQ4_XS (current)Decode 311.94 · Prefill 1321.43 ·

Core figures

Decode (avg)
311.94 tok/s
Prefill (avg)
1,321.43 tok/s
TTFT (avg)
0.8 s
VRAM (avg)
6.76 GB
MTP acceptance rate
0.71
TTFB
2.5 GB
Power draw
230.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.2-3B-Instruct
Quantization
IQ4_XS
Framework
Strata
Version
v0.29
Context length
4096 tokens
Batch size
256
GPU layers
5
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)
6.76 GB
OS
Ubuntu 22.04
Driver
amdgpu-pro 24.20
CUDA
12.8
Power draw
230.1 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

    v0.29 · Ubuntu 22.04 · CUDA 12.8 · 4096 ctx

    311.94 tok/s

    Decode

    1,321.43 tok/s

    Prefill

    0.8 s

    TTFT

    6.76 GB

    VRAM

    0.71

    MTP

    230.1 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=16 running model_id=70 at IQ4_XS