Arao AI
Back to search results

Qwen3.5-0.8B · IQ2_M

Start a discussion
Apple M5 Pro64GBvLLM v0.33L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ2_M) on Apple M5 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

323.11 tok/s

Decode

Decode speed

1,474.14 tok/s

Prefill

Prefill speed

0.67 s

TTFT

Time to first token

2.97 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. llama.cpp · IQ1_S Decode 341.6 · Prefill 1406.03 ·
  2. vLLM · IQ2_M (current)Decode 323.11 · Prefill 1474.14 ·
  3. vLLM · Q3_K_M Decode 358.52 · Prefill 1906.72 ·

Core figures

Decode (avg)
323.11 tok/s
Prefill (avg)
1,474.14 tok/s
TTFT (avg)
0.67 s
VRAM (avg)
2.97 GB
MTP acceptance rate
—
TTFB
2.58 GB
Power draw
138.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ2_M
Framework
vLLM
Version
v0.33
Context length
2048 tokens
Batch size
8
GPU layers
999
Flash Attention
Off

Hardware

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

GPU
Apple M5 Pro
Nominal VRAM
64 GB
Measured VRAM (avg)
2.97 GB
OS
macOS 15.0
Driver
Apple M5 Pro
CUDA
N/A
Power draw
138.2 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.33 · macOS 15.0 · CUDA N/A · 2048 ctx

    323.11 tok/s

    Decode

    1,474.14 tok/s

    Prefill

    0.67 s

    TTFT

    2.97 GB

    VRAM

    —

    MTP

    138.2 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=27 running model_id=51 at IQ2_M