← Back to community benchmarks

Qwen3.5-35B-A3B

M2 Ultra (60c) · 128 GB · 4bit · 2026-03-11
Performance
4k
tokens
1,148
PP tok/s
76.1
TG tok/s
3569
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 128 GB
GPU Cores 60
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,095 78.2 20.1 GB view
4k 1,148 76.1 20.2 GB current
8k 1,129 71.5 20.4 GB view
Batching Results
Batch Size TG tok/s Speedup
78.2 1.00×
132.2 1.69×
194.3 2.48×