← Back to community benchmarks

Qwen3.5-35B-A3B-oQ4e

M5 Max (40c) · 128 GB · 4bit · 2026-04-14
Performance
64k
tokens
1,492
PP tok/s
48.8
TG tok/s
43921
TTFT (ms)
45.4
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5
macOS macOS 26.4
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,390 199.2 40.0 GB view
8k 1,039 100.7 40.7 GB view
64k 1,492 48.8 45.4 GB current