Arao AI
Back to search results

Qwen3.5-4B · IQ1_S

Start a discussion
AMD Radeon RX 9070 GRE12GBvLLM v0.21L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (IQ1_S) on AMD Radeon RX 9070 GRE with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

165.6 tok/s

Decode

Decode speed

729.98 tok/s

Prefill

Prefill speed

1.17 s

TTFT

Time to first token

5.63 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 165.6 · Prefill 729.98 ·
  2. Strata · IQ1_S Decode 212.06 · Prefill 968.79 ·

Core figures

Decode (avg)
165.6 tok/s
Prefill (avg)
729.98 tok/s
TTFT (avg)
1.17 s
VRAM (avg)
5.63 GB
MTP acceptance rate
—
TTFB
1.32 GB
Power draw
238.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
IQ1_S
Framework
vLLM
Version
v0.21
Context length
8192 tokens
Batch size
32
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 GRE
Nominal VRAM
12 GB
Measured VRAM (avg)
5.63 GB
OS
Windows 11 23H2
Driver
amdgpu 6.10
CUDA
N/A
Power draw
238.7 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

    v0.21 · Windows 11 23H2 · CUDA N/A · 8192 ctx

    165.6 tok/s

    Decode

    729.98 tok/s

    Prefill

    1.17 s

    TTFT

    5.63 GB

    VRAM

    —

    MTP

    238.7 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=32 running model_id=48 at IQ1_S