Arao AI
Back to search results

Qwen3.5-4B · IQ3_S

Start a discussion
Intel Arc B58012GBStrata v0.43L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (IQ3_S) on Intel Arc B580 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

101.32 tok/s

Decode

Decode speed

490.59 tok/s

Prefill

Prefill speed

2.38 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 · IQ1_S Decode 98.24 · Prefill 506.66 ·
  2. llama.cpp · Q3_K_L Decode 70.52 · Prefill 317.93 ·
  3. vLLM · Q2_K Decode 89.29 · Prefill 348.31 ·
  4. Strata · IQ3_S (current)Decode 101.32 · Prefill 490.59 ·

Core figures

Decode (avg)
101.32 tok/s
Prefill (avg)
490.59 tok/s
TTFT (avg)
2.38 s
VRAM (avg)
7.64 GB
MTP acceptance rate
0.59
TTFB
0.81 GB
Power draw
167.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
IQ3_S
Framework
Strata
Version
v0.43
Context length
4096 tokens
Batch size
256
GPU layers
12
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
Intel Arc B580
Nominal VRAM
12 GB
Measured VRAM (avg)
7.64 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
167.1 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

    v0.43 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx

    101.32 tok/s

    Decode

    490.59 tok/s

    Prefill

    2.38 s

    TTFT

    7.64 GB

    VRAM

    0.59

    MTP

    167.1 W

    Power draw

    L2 batch seed 2026-10-10: Strata on hw_id=94 running model_id=48 at IQ3_S