Arao AI
Back to search results

Qwen3-1.7B · IQ1_S

Start a discussion
AMD Radeon RX 907016GBllama.cpp v0.38L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (IQ1_S) on AMD Radeon RX 9070 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

251.73 tok/s

Decode

Decode speed

1,075.85 tok/s

Prefill

Prefill speed

1.85 s

TTFT

Time to first token

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

Core figures

Decode (avg)
251.73 tok/s
Prefill (avg)
1,075.85 tok/s
TTFT (avg)
1.85 s
VRAM (avg)
3.6 GB
MTP acceptance rate
—
TTFB
2.01 GB
Power draw
319.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
IQ1_S
Framework
llama.cpp
Version
v0.38
Context length
4096 tokens
Batch size
512
GPU layers
28
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)
3.6 GB
OS
Ubuntu 24.04
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
319.2 W

Sources & evidence

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

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

    v0.38 · Ubuntu 24.04 · CUDA N/A · 4096 ctx

    251.73 tok/s

    Decode

    1,075.85 tok/s

    Prefill

    1.85 s

    TTFT

    3.6 GB

    VRAM

    —

    MTP

    319.2 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=21 running model_id=55 at IQ1_S