← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Ultra (60c) · 96 GB · 8bit · 2026-06-04
Performance
4k
tokens
1,968
PP tok/s
76.4
TG tok/s
2081
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.4.1
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,409 80.9 35.4 GB view
4k 1,968 76.4 36.2 GB current
16k 1,929 72.0 37.1 GB view
128k 831.4 44.9 46.5 GB view
195k 595.3 35.0 54.8 GB view
Batching Results
Batch Size TG tok/s Speedup
80.9 1.00×
132.3 1.64×
202.7 2.51×