Arao AI
Back to search results

Qwen3-Embedding-0.6B · Q4_K_S

Start a discussion
Apple M5 Pro64GBOllama v0.54L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q4_K_S) on Apple M5 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

342.8 tok/s

Decode

Decode speed

1,259.06 tok/s

Prefill

Prefill speed

2.47 s

TTFT

Time to first token

3.09 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 286.68 · Prefill 1382.17 ·
  2. llama.cpp · IQ2_M Decode 301.75 · Prefill 1278.13 ·
  3. Ollama · Q4_K_S (current)Decode 342.8 · Prefill 1259.06 ·

Core figures

Decode (avg)
342.8 tok/s
Prefill (avg)
1,259.06 tok/s
TTFT (avg)
2.47 s
VRAM (avg)
3.09 GB
MTP acceptance rate
—
TTFB
2.74 GB
Power draw
145 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
Q4_K_S
Framework
Ollama
Version
v0.54
Context length
16384 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
Apple M5 Pro
Nominal VRAM
64 GB
Measured VRAM (avg)
3.09 GB
OS
macOS 15.0
Driver
Apple M5 Pro
CUDA
N/A
Power draw
145 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

    v0.54 · macOS 15.0 · CUDA N/A · 16384 ctx

    342.8 tok/s

    Decode

    1,259.06 tok/s

    Prefill

    2.47 s

    TTFT

    3.09 GB

    VRAM

    —

    MTP

    145 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=27 running model_id=62 at Q4_K_S