Arao AI
Back to search results

Qwen3.5-0.8B · Q3_K_M

Start a discussion
Intel Arc B58012GBOllama v0.49L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q3_K_M) on Intel Arc B580 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

110.96 tok/s

Decode

Decode speed

517.6 tok/s

Prefill

Prefill speed

0.71 s

TTFT

Time to first token

3.24 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. Ollama · Q3_K_M (current)Decode 110.96 · Prefill 517.6 ·
  2. Strata · Q5_K_M Decode 136.37 · Prefill 553.15 ·
  3. llama.cpp · Q4_K_M Decode 117.19 · Prefill 568.87 ·
  4. vLLM · Q4_K_S Decode 137.77 · Prefill 674.05 ·

Core figures

Decode (avg)
110.96 tok/s
Prefill (avg)
517.6 tok/s
TTFT (avg)
0.71 s
VRAM (avg)
3.24 GB
MTP acceptance rate
—
TTFB
0.89 GB
Power draw
157 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q3_K_M
Framework
Ollama
Version
v0.49
Context length
16384 tokens
Batch size
256
GPU layers
99
Flash Attention
Off

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)
3.24 GB
OS
Windows 11 24H2
Driver
Intel Arc 32.0.101.6552
CUDA
12.6
Power draw
157 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.49 · Windows 11 24H2 · CUDA 12.6 · 16384 ctx

    110.96 tok/s

    Decode

    517.6 tok/s

    Prefill

    0.71 s

    TTFT

    3.24 GB

    VRAM

    —

    MTP

    157 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=94 running model_id=51 at Q3_K_M