Arao AI
Back to search results

Qwen3-1.7B · IQ3_XS

Start a discussion
AMD Radeon RX 907016GBStrata v0.20L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (IQ3_XS) on AMD Radeon RX 9070 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

263.09 tok/s

Decode

Decode speed

972.27 tok/s

Prefill

Prefill speed

1.25 s

TTFT

Time to first token

4.32 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. llama.cpp · IQ1_S Decode 251.73 · Prefill 1075.85 ·
  2. llama.cpp · Q3_K_L Decode 168.28 · Prefill 901.02 ·
  3. Strata · IQ3_XS (current)Decode 263.09 · Prefill 972.27 ·
  4. Strata · Q5_K_M Decode 186.72 · Prefill 727.73 ·

Core figures

Decode (avg)
263.09 tok/s
Prefill (avg)
972.27 tok/s
TTFT (avg)
1.25 s
VRAM (avg)
4.32 GB
MTP acceptance rate
0.53
TTFB
2.1 GB
Power draw
284.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
IQ3_XS
Framework
Strata
Version
v0.20
Context length
16384 tokens
Batch size
512
GPU layers
15
Flash Attention
Off

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)
4.32 GB
OS
Windows 11 23H2
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
284.1 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.20 · Windows 11 23H2 · CUDA N/A · 16384 ctx

    263.09 tok/s

    Decode

    972.27 tok/s

    Prefill

    1.25 s

    TTFT

    4.32 GB

    VRAM

    0.53

    MTP

    284.1 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=21 running model_id=55 at IQ3_XS