← Back to community benchmarks

Qwen3.5-35B-A3B

M2 Ultra (60c) · 64 GB · 4bit · 2026-03-12
Performance
1k
tokens
1,025
PP tok/s
77.4
TG tok/s
999
TTFT (ms)
20.1
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 64 GB
GPU Cores 60
Software
oMLX v0.2.9
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,025 77.4 20.1 GB current
4k 1,142 73.4 20.2 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 77.4 1.00×
2× 127.5 1.65×
4× 190.8 2.47×