← Back to community benchmarks

Qwen3.5-4B

M1 Max (32c) · 64 GB · 4bit · 2026-03-10
Performance
4k
tokens
578.8
PP tok/s
79.2
TG tok/s
7076
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.2.6
macOS macOS 26.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 570.5 87.4 4.0 GB view
4k 578.8 79.2 4.2 GB current
8k 569.5 73.1 4.6 GB view
16k 545.2 64.2 5.3 GB view
Batching Results
Batch Size TG tok/s Speedup
87.4 1.00×
109.2 1.25×
123.8 1.42×
99.4 1.14×