Arao AI
Back to search results

Qwen3.5-4B · IQ1_S

Start a discussion
AMD Radeon RX 9070 GRE12GBStrata v0.33L2 Cross-framework verified

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

212.06 tok/s

Decode

Decode speed

968.79 tok/s

Prefill

Prefill speed

2.12 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 Decode 165.6 · Prefill 729.98 ·
  2. Strata · IQ1_S (current)Decode 212.06 · Prefill 968.79 ·

Core figures

Decode (avg)
212.06 tok/s
Prefill (avg)
968.79 tok/s
TTFT (avg)
2.12 s
VRAM (avg)
5.63 GB
MTP acceptance rate
0.6
TTFB
1.7 GB
Power draw
247.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
IQ1_S
Framework
Strata
Version
v0.33
Context length
32768 tokens
Batch size
256
GPU layers
8
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
Ubuntu 22.04
Driver
amdgpu 6.10
CUDA
N/A
Power draw
247.2 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

    v0.33 · Ubuntu 22.04 · CUDA N/A · 32768 ctx

    212.06 tok/s

    Decode

    968.79 tok/s

    Prefill

    2.12 s

    TTFT

    5.63 GB

    VRAM

    0.6

    MTP

    247.2 W

    Power draw

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