Arao AI
Back to search results

Qwen3.5-0.8B · Q4_K_M

Start a discussion
Intel Arc B58012GBllama.cpp v0.36L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q4_K_M) on Intel Arc B580 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

117.19 tok/s

Decode

Decode speed

568.87 tok/s

Prefill

Prefill speed

1.57 s

TTFT

Time to first token

3.48 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · Q4_K_M (current)Decode 117.19 · Prefill 568.87 ·
  2. vLLM · Q4_K_S Decode 137.77 · Prefill 674.05 ·

Core figures

Decode (avg)
117.19 tok/s
Prefill (avg)
568.87 tok/s
TTFT (avg)
1.57 s
VRAM (avg)
3.48 GB
MTP acceptance rate
—
TTFB
0.94 GB
Power draw
237.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q4_K_M
Framework
llama.cpp
Version
v0.36
Context length
8192 tokens
Batch size
512
GPU layers
99
Flash Attention
On

Hardware

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

GPU
Intel Arc B580
Nominal VRAM
12 GB
Measured VRAM (avg)
3.48 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
237.7 W

Sources & evidence

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

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

    v0.36 · Ubuntu 24.04 · CUDA 12.6 · 8192 ctx

    117.19 tok/s

    Decode

    568.87 tok/s

    Prefill

    1.57 s

    TTFT

    3.48 GB

    VRAM

    —

    MTP

    237.7 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=94 running model_id=51 at Q4_K_M