← Back to community benchmarks

Qwen3.5-35B-A3B

M3 Ultra (60c) · 256 GB · unknown · 2026-04-12
Performance
4k
tokens
2,108
PP tok/s
70.0
TG tok/s
1943
TTFT (ms)
66.4
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.5.dev1
macOS macOS 26.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,450 71.6 65.7 GB view
4k 2,108 70.0 66.4 GB current
8k 2,168 64.8 66.8 GB view
Batching Results
Batch Size TG tok/s Speedup
71.6 1.00×
67.0 0.94×
116.5 1.63×