← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Max (40c) · 48 GB · 6bit · 2026-03-09
Performance
4k
tokens
1,624
PP tok/s
86.5
TG tok/s
2522
TTFT (ms)
28.3
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 15.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,487 90.2 28.1 GB view
4k 1,624 86.5 28.3 GB current
Batching Results
Batch Size TG tok/s Speedup
90.2 1.00×
145.6 1.61×
199.8 2.22×
247.8 2.75×