Arao AI
Back to search results

Qwen3.5-9B · IQ1_S

Start a discussion
AMD Radeon RX 9070 XT16GBvLLM v0.29L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-9B (IQ1_S) on AMD Radeon RX 9070 XT with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

133.24 tok/s

Decode

Decode speed

623.53 tok/s

Prefill

Prefill speed

1.96 s

TTFT

Time to first token

10.04 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 · IQ1_S (current)Decode 133.24 · Prefill 623.53 ·
  2. vLLM · Q3_K_S Decode 113.68 · Prefill 457.77 ·
  3. Ollama · IQ2_XS Decode 124.46 · Prefill 417.76 ·

Core figures

Decode (avg)
133.24 tok/s
Prefill (avg)
623.53 tok/s
TTFT (avg)
1.96 s
VRAM (avg)
10.04 GB
MTP acceptance rate
—
TTFB
1.07 GB
Power draw
239.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-9B
Quantization
IQ1_S
Framework
vLLM
Version
v0.29
Context length
4096 tokens
Batch size
8
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 RX 9070 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
10.04 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.10
CUDA
N/A
Power draw
239.4 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

    v0.29 · Ubuntu 22.04 · CUDA N/A · 4096 ctx

    133.24 tok/s

    Decode

    623.53 tok/s

    Prefill

    1.96 s

    TTFT

    10.04 GB

    VRAM

    —

    MTP

    239.4 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=16 running model_id=49 at IQ1_S