← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Max (40c) · 128 GB · 4bit · 2026-03-09
Performance
1k
tokens
1,216
PP tok/s
122.2
TG tok/s
842
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,216 122.2 18.2 GB current
4k 1,622 117.6 18.4 GB view
8k 1,635 110.4 18.6 GB view
16k 1,544 97.1 19.0 GB view
Batching Results
Batch Size TG tok/s Speedup
122.2 1.00×
205.3 1.68×
283.6 2.32×