Arao AI
Back to search results

Qwen3.5-4B · IQ3_S

Start a discussion
AMD Radeon RX 7900 XTX24GBOllama v0.50L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (IQ3_S) on AMD Radeon RX 7900 XTX with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

128.5 tok/s

Decode

Decode speed

561.01 tok/s

Prefill

Prefill speed

2.44 s

TTFT

Time to first token

7.64 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. Ollama · IQ3_S (current)Decode 128.5 · Prefill 561.01 ·
  2. Strata · Q3_K_M Decode 202.56 · Prefill 756.52 ·

Core figures

Decode (avg)
128.5 tok/s
Prefill (avg)
561.01 tok/s
TTFT (avg)
2.44 s
VRAM (avg)
7.64 GB
MTP acceptance rate
—
TTFB
1.03 GB
Power draw
282.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
IQ3_S
Framework
Ollama
Version
v0.50
Context length
2048 tokens
Batch size
512
GPU layers
33
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 7900 XTX
Nominal VRAM
24 GB
Measured VRAM (avg)
7.64 GB
OS
macOS 15.0
Driver
560.94
CUDA
12.6
Power draw
282.9 W

Sources & evidence

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

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

    v0.50 · macOS 15.0 · CUDA 12.6 · 2048 ctx

    128.5 tok/s

    Decode

    561.01 tok/s

    Prefill

    2.44 s

    TTFT

    7.64 GB

    VRAM

    —

    MTP

    282.9 W

    Power draw

    L2 batch seed 2026-10-10: Ollama on hw_id=11 running model_id=48 at IQ3_S