Back to search results
Qwen3-Embedding-0.6B · Q5_K_M
Apple M2 ProOllama v0.23L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q5_K_M) on Apple M2 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
141.79 tok/s
Decode
Decode speed
490.44 tok/s
Prefill
Prefill speed
1.38 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
- vLLM · Q5_K_M Decode 162.76 · Prefill 684.58 ·
- Ollama · Q5_K_M (current)Decode 141.79 · Prefill 490.44 ·
Core figures
- Decode (avg)
- 141.79 tok/s
- Prefill (avg)
- 490.44 tok/s
- TTFT (avg)
- 1.38 s
- VRAM (avg)
- 3.28 GB
- MTP acceptance rate
- —
- TTFB
- 1.13 GB
- Power draw
- 19.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Embedding-0.6B
- Quantization
- Q5_K_M
- Framework
- Ollama
- Version
- v0.23
- Context length
- 8192 tokens
- Batch size
- 512
- GPU layers
- 33
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M2 Pro
- Measured VRAM (avg)
- 3.28 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Pro
- CUDA
- N/A
- Power draw
- 19.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.23 · macOS 15.0 · CUDA N/A · 8192 ctx
141.79 tok/s
Decode
490.44 tok/s
Prefill
1.38 s
TTFT
3.28 GB
VRAM
—
MTP
19.2 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=102 running model_id=62 at Q5_K_M