Arao AI
Back to search results

Qwen3.5-4B · IQ3_S

Start a discussion
AMD Radeon RX 7900 XTX24GBStrata v0.35L2 Cross-framework verified

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

166.71 tok/s

Decode

Decode speed

815.55 tok/s

Prefill

Prefill speed

0.29 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. llama.cpp · Q3_K_S Decode 122.17 · Prefill 596.11 ·
  2. Strata · IQ3_S (current)Decode 166.71 · Prefill 815.55 ·
  3. Ollama · IQ3_S Decode 128.5 · Prefill 561.01 ·
  4. Strata · Q3_K_M Decode 202.56 · Prefill 756.52 ·

Core figures

Decode (avg)
166.71 tok/s
Prefill (avg)
815.55 tok/s
TTFT (avg)
0.29 s
VRAM (avg)
7.64 GB
MTP acceptance rate
0.74
TTFB
1.33 GB
Power draw
211.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
IQ3_S
Framework
Strata
Version
v0.35
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 7900 XTX
Nominal VRAM
24 GB
Measured VRAM (avg)
7.64 GB
OS
Ubuntu 24.04
Driver
amdgpu-pro 24.20
CUDA
12.8
Power draw
211.2 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.35 · Ubuntu 24.04 · CUDA 12.8 · 32768 ctx

    166.71 tok/s

    Decode

    815.55 tok/s

    Prefill

    0.29 s

    TTFT

    7.64 GB

    VRAM

    0.74

    MTP

    211.2 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=11 running model_id=48 at IQ3_S