Back to search results
Qwen3-Embedding-0.6B · Q6_K
Apple M5 Max128GBllama.cpp v0.50L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q6_K) on Apple M5 Max with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
297.37 tok/s
Decode
Decode speed
1,423.38 tok/s
Prefill
Prefill speed
1.96 s
TTFT
Time to first token
3.36 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · Q6_K (current)Decode 297.37 · Prefill 1423.38 ·
- vLLM · FP16 Decode 257.66 · Prefill 966.33 ·
- vLLM · IQ2_M Decode 302.89 · Prefill 1094.91 ·
- Ollama · IQ3_XS Decode 290.71 · Prefill 1516.13 ·
Core figures
- Decode (avg)
- 297.37 tok/s
- Prefill (avg)
- 1,423.38 tok/s
- TTFT (avg)
- 1.96 s
- VRAM (avg)
- 3.36 GB
- MTP acceptance rate
- —
- TTFB
- 2.38 GB
- Power draw
- 254.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Embedding-0.6B
- Quantization
- Q6_K
- Framework
- llama.cpp
- Version
- v0.50
- Context length
- 8192 tokens
- Batch size
- 256
- GPU layers
- 20
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- Apple M5 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 3.36 GB
- OS
- Ubuntu 22.04
- Driver
- 570.86
- CUDA
- 12.4
- Power draw
- 254.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.50 · Ubuntu 22.04 · CUDA 12.4 · 8192 ctx
297.37 tok/s
Decode
1,423.38 tok/s
Prefill
1.96 s
TTFT
3.36 GB
VRAM
—
MTP
254.1 W
Power draw
L2 batch seed 2026-10-16: llama.cpp on hw_id=28 running model_id=62 at Q6_K