← Back to community benchmarks

Qwen3.5-35B-A3B

M3 Max (40c) · 64 GB · 8bit · 2026-03-09
Performance
1k
tokens
1,436
PP tok/s
69.3
TG tok/s
713
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 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 1,436 69.3 36.2 GB current
4k 1,446 65.6 36.3 GB view
Batching Results
Batch Size TG tok/s Speedup
69.3 1.00×
113.5 1.64×
172.2 2.48×