Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · IQ2_M

Start a discussion
Intel Arc A770 16GB16GBvLLM v0.36L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ2_M) on Intel Arc A770 16GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

228.63 tok/s

Decode

Decode speed

1,047.8 tok/s

Prefill

Prefill speed

1.22 s

TTFT

Time to first token

2.65 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 Decode 232.59 · Prefill 880.44 ·
  4. vLLM · IQ2_M (current)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)
228.63 tok/s
Prefill (avg)
1,047.8 tok/s
TTFT (avg)
1.22 s
VRAM (avg)
2.65 GB
MTP acceptance rate
—
TTFB
1.83 GB
Power draw
190.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
IQ2_M
Framework
vLLM
Version
v0.36
Context length
2048 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)
2.65 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
190.4 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

    v0.36 · Ubuntu 24.04 · CUDA 12.6 · 2048 ctx

    228.63 tok/s

    Decode

    1,047.8 tok/s

    Prefill

    1.22 s

    TTFT

    2.65 GB

    VRAM

    —

    MTP

    190.4 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=97 running model_id=59 at IQ2_M