← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Pro (20c) · 64 GB · 4bit · 2026-03-09
Performance
1k
tokens
840.7
PP tok/s
81.8
TG tok/s
1218
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.2.6
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 840.7 81.8 20.0 GB current
4k 885.2 77.0 20.2 GB view
Batching Results
Batch Size TG tok/s Speedup
81.8 1.00×
134.9 1.65×
168.3 2.06×