← Back to community benchmarks

Qwen3-Embedding-4B-4bit-DWQ

M4 (10c) · 24 GB · 4bit · 2026-03-11
Performance
4k
tokens
348.4
PP tok/s
32.3
TG tok/s
11759
TTFT (ms)
3.2
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 384.4 38.7 2.7 GB view
4k 348.4 32.3 3.2 GB current
Batching Results
Batch Size TG tok/s Speedup
38.7 1.00×
72.9 1.88×
87.8 2.27×