← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-09
Performance
4k
tokens
66.7
PP tok/s
12.7
TG tok/s
61382
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 26.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 66.6 13.8 3.9 GB view
4k 66.7 12.7 4.2 GB current
Batching Results
Batch Size TG tok/s Speedup
13.8 1.00×
14.8 1.07×
15.0 1.09×