← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Pro (20c) · 48 GB · 4bit · 2026-05-20
Performance
1k
tokens
1,139
PP tok/s
97.7
TG tok/s
899
TTFT (ms)
19.3
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.9rc1
macOS macOS 26.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,139 97.7 19.3 GB current
4k 2,103 94.9 20.0 GB view
Batching Results
Batch Size TG tok/s Speedup
97.7 1.00×
149.2 1.53×
197.5 2.02×