← Back to community benchmarks

Qwen3.5-35B-A3BMXFP4

M2 Max (30c) · 64 GB · 4bit · 2026-04-14
Performance
32k
tokens
524.2
PP tok/s
31.7
TG tok/s
62507
TTFT (ms)
43.4
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 64 GB
GPU Cores 30
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 663.5 161.8 38.4 GB view
4k 618.3 74.9 38.9 GB view
8k 677.8 66.2 39.6 GB view
16k 617.6 53.9 40.8 GB view
32k 524.2 31.7 43.4 GB current