← Back to community benchmarks

Qwen3.5-35B-A3B-OptiQ

M2 Ultra (60c) · 64 GB · 4bit · 2026-07-21
Performance
64k
tokens
790.7
PP tok/s
54.3
TG tok/s
82882
TTFT (ms)
27.9
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 64 GB
GPU Cores 60
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,114 75.7 21.7 GB view
4k 1,213 73.7 22.5 GB view
8k 1,181 70.2 22.9 GB view
16k 1,110 67.0 23.5 GB view
32k 997.9 59.7 25.0 GB view
64k 790.7 54.3 27.9 GB current
Batching Results
Batch Size TG tok/s Speedup
75.7 1.00×
123.1 1.63×
246.4 3.25×
520.5 6.88×