Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · IQ1_S

Start a discussion
Intel Arc A770 16GB16GBvLLM v0.40L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ1_S) on Intel Arc A770 16GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

232.59 tok/s

Decode

Decode speed

880.44 tok/s

Prefill

Prefill speed

1.1 s

TTFT

Time to first token

2.54 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. llama.cpp · IQ3_XS Decode 195.32 · Prefill 695.93 ·
  2. llama.cpp · IQ4_XS Decode 170.02 · Prefill 839.84 ·
  3. vLLM · IQ1_S (current)Decode 232.59 · Prefill 880.44 ·
  4. vLLM · IQ2_M Decode 228.63 · Prefill 1047.8 ·
  5. Strata · Q3_K_M Decode 255.52 · Prefill 902.5 ·
  6. Strata · Q6_K Decode 176.77 · Prefill 757.14 ·

Core figures

Decode (avg)
232.59 tok/s
Prefill (avg)
880.44 tok/s
TTFT (avg)
1.1 s
VRAM (avg)
2.54 GB
MTP acceptance rate
—
TTFB
1.86 GB
Power draw
178.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
IQ1_S
Framework
vLLM
Version
v0.40
Context length
32768 tokens
Batch size
8
GPU layers
999
Flash Attention
On

Hardware

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

GPU
Intel Arc A770 16GB
Nominal VRAM
16 GB
Measured VRAM (avg)
2.54 GB
OS
Windows 11 23H2
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
178.1 W

Sources & evidence

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

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

    v0.40 · Windows 11 23H2 · CUDA 12.6 · 32768 ctx

    232.59 tok/s

    Decode

    880.44 tok/s

    Prefill

    1.1 s

    TTFT

    2.54 GB

    VRAM

    —

    MTP

    178.1 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=97 running model_id=59 at IQ1_S