Arao AI
Back to search results

Qwen3-Embedding-0.6B · Q5_K_M

Start a discussion
Apple M1 ProvLLM v0.51L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q5_K_M) on Apple M1 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

164.4 tok/s

Decode

Decode speed

839.01 tok/s

Prefill

Prefill speed

0.93 s

TTFT

Time to first token

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

Core figures

Decode (avg)
164.4 tok/s
Prefill (avg)
839.01 tok/s
TTFT (avg)
0.93 s
VRAM (avg)
3.28 GB
MTP acceptance rate
—
TTFB
1.32 GB
Power draw
63.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
Q5_K_M
Framework
vLLM
Version
v0.51
Context length
16384 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 M1 Pro
Measured VRAM (avg)
3.28 GB
OS
macOS 15.0
Driver
Apple M1 Pro
CUDA
N/A
Power draw
63.1 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

    v0.51 · macOS 15.0 · CUDA N/A · 16384 ctx

    164.4 tok/s

    Decode

    839.01 tok/s

    Prefill

    0.93 s

    TTFT

    3.28 GB

    VRAM

    —

    MTP

    63.1 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=100 running model_id=62 at Q5_K_M