← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Max (40c) · 128 GB · 8bit · 2026-03-09
Performance
4k
tokens
1,629
PP tok/s
77.4
TG tok/s
2515
TTFT (ms)
36.3
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 15.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,441 80.7 36.2 GB view
4k 1,629 77.4 36.3 GB current
Batching Results
Batch Size TG tok/s Speedup
80.7 1.00×
136.7 1.69×
191.3 2.37×