← Back to community benchmarks

Qwen3-Embedding-0.6B-4bit-DWQ

M4 (10c) · 24 GB · 4bit · 2026-03-11
Performance
1k
tokens
2,017
PP tok/s
186.3
TG tok/s
508
TTFT (ms)
1.0
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,017 186.3 1.0 GB current
4k 1,819 106.7 1.3 GB view
Batching Results
Batch Size TG tok/s Speedup
186.3 1.00×
274.1 1.47×
323.0 1.73×