Arao AI
Back to search results

Qwen3-1.7B · Q4_K_S

Start a discussion
Intel Arc 140VStrata v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q4_K_S) on Intel Arc 140V with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

123.42 tok/s

Decode

Decode speed

651.16 tok/s

Prefill

Prefill speed

0.24 s

TTFT

Time to first token

4.88 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 · IQ2_M Decode 112.05 · Prefill 542.45 ·
  2. Ollama · Q5_K_S Decode 71.63 · Prefill 287.36 ·
  3. Strata · Q4_K_S (current)Decode 123.42 · Prefill 651.16 ·
  4. Strata · Q5_K_S Decode 111.13 · Prefill 553 ·

Core figures

Decode (avg)
123.42 tok/s
Prefill (avg)
651.16 tok/s
TTFT (avg)
0.24 s
VRAM (avg)
4.88 GB
MTP acceptance rate
0.62
TTFB
0.99 GB
Power draw
183.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q4_K_S
Framework
Strata
Version
v0.48
Context length
8192 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)
4.88 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
183.7 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

    v0.48 · Ubuntu 24.04 · CUDA 12.6 · 8192 ctx

    123.42 tok/s

    Decode

    651.16 tok/s

    Prefill

    0.24 s

    TTFT

    4.88 GB

    VRAM

    0.62

    MTP

    183.7 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=98 running model_id=55 at Q4_K_S