Back to search results
Qwen3-Embedding-0.6B · IQ3_XS
Apple M2 UltraStrata v0.40L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ3_XS) on Apple M2 Ultra with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
284.88 tok/s
Decode
Decode speed
1,247.89 tok/s
Prefill
Prefill speed
0.75 s
TTFT
Time to first token
2.88 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · FP16 Decode 152.68 · Prefill 595.8 ·
- vLLM · Q2_K Decode 308 · Prefill 1290.58 ·
- Strata · IQ3_XS (current)Decode 284.88 · Prefill 1247.89 ·
Core figures
- Decode (avg)
- 284.88 tok/s
- Prefill (avg)
- 1,247.89 tok/s
- TTFT (avg)
- 0.75 s
- VRAM (avg)
- 2.88 GB
- MTP acceptance rate
- 0.47
- TTFB
- 2.28 GB
- Power draw
- 59.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Embedding-0.6B
- Quantization
- IQ3_XS
- Framework
- Strata
- Version
- v0.40
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 8
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M2 Ultra
- Measured VRAM (avg)
- 2.88 GB
- OS
- macOS 15.0
- Driver
- Apple M2 Ultra
- CUDA
- N/A
- Power draw
- 59.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.40 · macOS 15.0 · CUDA N/A · 32768 ctx
284.88 tok/s
Decode
1,247.89 tok/s
Prefill
0.75 s
TTFT
2.88 GB
VRAM
0.47
MTP
59.9 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=103 running model_id=62 at IQ3_XS