← Back to community benchmarks

unsloth--Qwen3.6-35B-A3B-UD

M5 Max (40c) · 128 GB · 4bit · 2026-07-23
Performance
8k
tokens
4,476
PP tok/s
106.1
TG tok/s
1830
TTFT (ms)
21.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.3
macOS macOS 26.5.2
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,860 113.2 20.5 GB view
4k 4,601 107.9 21.3 GB view
8k 4,476 106.1 21.8 GB current
16k 4,124 101.5 22.5 GB view
32k 3,412 94.5 24.0 GB view
64k 1,212 80.7 26.4 GB view