← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Max (40c) · 64 GB · 4bit · 2026-03-09
Performance
8k
tokens
1,487
PP tok/s
90.0
TG tok/s
5509
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 26.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,652 93.4 20.1 GB view
4k 1,706 88.6 20.2 GB view
8k 1,487 90.0 20.4 GB current
16k 1,227 63.7 20.8 GB view
32k 1,026 42.5 21.6 GB view
Batching Results
Batch Size TG tok/s Speedup
93.4 1.00×
163.9 1.75×