Arao AI
Back to search results

Qwen3-Embedding-0.6B · Q2_K

Start a discussion
Apple M1 MaxOllama v0.42L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q2_K) on Apple M1 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

294.74 tok/s

Decode

Decode speed

1,454.22 tok/s

Prefill

Prefill speed

0.65 s

TTFT

Time to first token

2.79 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 · Q3_K_M Decode 253.55 · Prefill 1128.29 ·
  2. Ollama · Q2_K (current)Decode 294.74 · Prefill 1454.22 ·
  3. Ollama · Q3_K_L Decode 236.47 · Prefill 1174.1 ·

Core figures

Decode (avg)
294.74 tok/s
Prefill (avg)
1,454.22 tok/s
TTFT (avg)
0.65 s
VRAM (avg)
2.79 GB
MTP acceptance rate
—
TTFB
2.36 GB
Power draw
36.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
Q2_K
Framework
Ollama
Version
v0.42
Context length
8192 tokens
Batch size
256
GPU layers
28
Flash Attention
On

Hardware

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

GPU
Apple M1 Max
Measured VRAM (avg)
2.79 GB
OS
macOS 15.0
Driver
Apple M1 Max
CUDA
N/A
Power draw
36.3 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

    v0.42 · macOS 15.0 · CUDA N/A · 8192 ctx

    294.74 tok/s

    Decode

    1,454.22 tok/s

    Prefill

    0.65 s

    TTFT

    2.79 GB

    VRAM

    —

    MTP

    36.3 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=101 running model_id=62 at Q2_K