Arao AI
Back to search results

Qwen3-8B · IQ3_XS

Start a discussion
Intel Arc 140VStrata v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ3_XS) on Intel Arc 140V with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

87.91 tok/s

Decode

Decode speed

405.6 tok/s

Prefill

Prefill speed

0.39 s

TTFT

Time to first token

12.52 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. Ollama · Q4_K_M Decode 43.74 · Prefill 228.72 ·
  2. Ollama · Q4_K_S Decode 45.55 · Prefill 229.62 ·
  3. Strata · IQ3_XS (current)Decode 87.91 · Prefill 405.6 ·

Core figures

Decode (avg)
87.91 tok/s
Prefill (avg)
405.6 tok/s
TTFT (avg)
0.39 s
VRAM (avg)
12.52 GB
MTP acceptance rate
0.47
TTFB
0.7 GB
Power draw
173.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ3_XS
Framework
Strata
Version
v0.34
Context length
8192 tokens
Batch size
512
GPU layers
5
Flash Attention
On

Hardware

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

GPU
Intel Arc 140V
Measured VRAM (avg)
12.52 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
173.5 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.34 · Ubuntu 24.04 · CUDA 12.6 · 8192 ctx

    87.91 tok/s

    Decode

    405.6 tok/s

    Prefill

    0.39 s

    TTFT

    12.52 GB

    VRAM

    0.47

    MTP

    173.5 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=98 running model_id=53 at IQ3_XS