Back to search results

Qwen3.8-9B · Q4_K_S

Start a discussion
Intel Arc 140VStrata v0.47L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q4_K_S) on Intel Arc 140V with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

62.42 tok/s

Decode

Decode speed

214.01 tok/s

Prefill

Prefill speed

1.39 s

TTFT

Time to first token

15.2 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. Strata · Q4_K_S (current)Decode 62.42 · Prefill 214.01 ·

Core figures

Decode (avg)
62.42 tok/s
Prefill (avg)
214.01 tok/s
TTFT (avg)
1.39 s
VRAM (avg)
15.2 GB
MTP acceptance rate
0.68
TTFB
0.5 GB
Power draw
195.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q4_K_S
Framework
Strata
Version
v0.47
Context length
2048 tokens
Batch size
512
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
Intel Arc 140V
Measured VRAM (avg)
15.2 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
195.2 W

Sources & evidence

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

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

    v0.47 · Ubuntu 24.04 · CUDA 12.6 · 2048 ctx

    62.42 tok/s

    Decode

    214.01 tok/s

    Prefill

    1.39 s

    TTFT

    15.2 GB

    VRAM

    0.68

    MTP

    195.2 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=98 running model_id=52 at Q4_K_S