← Back to community benchmarks

Qwen3.5-4B

M1 (7c) · 8 GB · 4bit · 2026-03-11
Performance
4k
tokens
125.7
PP tok/s
21.4
TG tok/s
32580
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M1 (7c)
Memory 8 GB
GPU Cores 7
Software
oMLX v0.2.7
macOS macOS 15.7.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 126.0 22.5 3.9 GB view
4k 125.7 21.4 4.2 GB current
Batching Results
Batch Size TG tok/s Speedup
22.5 1.00×
29.2 1.30×
30.3 1.35×