← Back to community benchmarks

Qwen3.6-35B-A3B-oQ8e

M4 Max (40c) · 64 GB · 8bit · 2026-04-28
Performance
4k
tokens
1,666
PP tok/s
80.5
TG tok/s
2459
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8.dev3
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,263 80.8 35.4 GB view
4k 1,666 80.5 36.2 GB current
8k 1,552 77.1 36.5 GB view
Batching Results
Batch Size TG tok/s Speedup
80.8 1.00×
135.7 1.68×
192.1 2.38×
251.7 3.12×