Arao AI
Back to search results

Qwen3-1.7B · Q3_K_S

Start a discussion
AMD Radeon AI PRO R970032GBvLLM v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q3_K_S) on AMD Radeon AI PRO R9700 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

272.77 tok/s

Decode

Decode speed

1,363 tok/s

Prefill

Prefill speed

0.6 s

TTFT

Time to first token

4.42 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. vLLM · Q3_K_S (current)Decode 272.77 · Prefill 1363 ·
  2. Ollama · IQ4_XS Decode 192.57 · Prefill 691.62 ·

Core figures

Decode (avg)
272.77 tok/s
Prefill (avg)
1,363 tok/s
TTFT (avg)
0.6 s
VRAM (avg)
4.42 GB
MTP acceptance rate
—
TTFB
2.18 GB
Power draw
246.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q3_K_S
Framework
vLLM
Version
v0.34
Context length
8192 tokens
Batch size
16
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 AI PRO R9700
Nominal VRAM
32 GB
Measured VRAM (avg)
4.42 GB
OS
Windows 11 23H2
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
246.3 W

Sources & evidence

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

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

    v0.34 · Windows 11 23H2 · CUDA N/A · 8192 ctx

    272.77 tok/s

    Decode

    1,363 tok/s

    Prefill

    0.6 s

    TTFT

    4.42 GB

    VRAM

    —

    MTP

    246.3 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=79 running model_id=55 at Q3_K_S