← Back to community benchmarks

Qwen3.6-35B-A3B-oQ8-mtp

M5 Max (40c) · 128 GB · 8bit · 2026-05-18
Performance
4k
tokens
3,464
PP tok/s
93.1
TG tok/s
1183
TTFT (ms)
37.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,963 97.8 36.2 GB view
4k 3,464 93.1 37.0 GB current
Batching Results
Batch Size TG tok/s Speedup
97.8 1.00×
142.8 1.46×
215.0 2.20×