Back to search results
Qwen3-Embedding-0.6B · Q5_K_M
Apple M4 Pro64GBvLLM v0.26L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q5_K_M) on Apple M4 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
270.98 tok/s
Decode
Decode speed
944.94 tok/s
Prefill
Prefill speed
1.46 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
5 days ago
Last verified
Performance
- vLLM · Q5_K_M (current)Decode 270.98 · Prefill 944.94 ·
Core figures
- Decode (avg)
- 270.98 tok/s
- Prefill (avg)
- 944.94 tok/s
- TTFT (avg)
- 1.46 s
- VRAM (avg)
- 3.28 GB
- MTP acceptance rate
- —
- TTFB
- 2.17 GB
- Power draw
- 58.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Embedding-0.6B
- Quantization
- Q5_K_M
- Framework
- vLLM
- Version
- v0.26
- Context length
- 2048 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 M4 Pro
- Nominal VRAM
- 64 GB
- Measured VRAM (avg)
- 3.28 GB
- OS
- macOS 15.0
- Driver
- Apple M4 Pro
- CUDA
- N/A
- Power draw
- 58.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.26 · macOS 15.0 · CUDA N/A · 2048 ctx
270.98 tok/s
Decode
944.94 tok/s
Prefill
1.46 s
TTFT
3.28 GB
VRAM
—
MTP
58.7 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=25 running model_id=62 at Q5_K_M