Arao AI
Back to search results

Qwen3-Embedding-0.6B · IQ1_S

Start a discussion
Apple M1 ProOllama v0.36L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ1_S) on Apple M1 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

247.65 tok/s

Decode

Decode speed

966.62 tok/s

Prefill

Prefill speed

2.49 s

TTFT

Time to first token

2.62 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. vLLM · Q5_K_M Decode 164.4 · Prefill 839.01 ·
  2. Ollama · IQ1_S (current)Decode 247.65 · Prefill 966.62 ·
  3. Ollama · Q4_K_S Decode 189.92 · Prefill 934.37 ·

Core figures

Decode (avg)
247.65 tok/s
Prefill (avg)
966.62 tok/s
TTFT (avg)
2.49 s
VRAM (avg)
2.62 GB
MTP acceptance rate
—
TTFB
1.98 GB
Power draw
52.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
IQ1_S
Framework
Ollama
Version
v0.36
Context length
4096 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 M1 Pro
Measured VRAM (avg)
2.62 GB
OS
macOS 15.0
Driver
Apple M1 Pro
CUDA
N/A
Power draw
52.3 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

    v0.36 · macOS 15.0 · CUDA N/A · 4096 ctx

    247.65 tok/s

    Decode

    966.62 tok/s

    Prefill

    2.49 s

    TTFT

    2.62 GB

    VRAM

    —

    MTP

    52.3 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=100 running model_id=62 at IQ1_S