Arao AI
Back to search results

Qwen3.5-0.8B · IQ2_XS

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

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ2_XS) on Intel Arc 140V with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

182.97 tok/s

Decode

Decode speed

879.22 tok/s

Prefill

Prefill speed

1.98 s

TTFT

Time to first token

2.91 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 · IQ2_XS (current)Decode 182.97 · Prefill 879.22 ·
  2. llama.cpp · Q5_K_S Decode 107.85 · Prefill 550.79 ·
  3. Strata · IQ2_M Decode 226.68 · Prefill 945.06 ·
  4. Strata · IQ4_XS Decode 175.73 · Prefill 704.21 ·

Core figures

Decode (avg)
182.97 tok/s
Prefill (avg)
879.22 tok/s
TTFT (avg)
1.98 s
VRAM (avg)
2.91 GB
MTP acceptance rate
—
TTFB
1.46 GB
Power draw
202.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ2_XS
Framework
llama.cpp
Version
v0.48
Context length
2048 tokens
Batch size
256
GPU layers
33
Flash Attention
Off

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)
2.91 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
202.4 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

    v0.48 · Ubuntu 24.04 · CUDA 12.6 · 2048 ctx

    182.97 tok/s

    Decode

    879.22 tok/s

    Prefill

    1.98 s

    TTFT

    2.91 GB

    VRAM

    —

    MTP

    202.4 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=98 running model_id=51 at IQ2_XS