← Back to community benchmarks

Qwen3.5-35B-A3BMXFP4

M2 Max (30c) · 64 GB · 4bit · 2026-04-14
Performance
8k
tokens
722.6
PP tok/s
53.1
TG tok/s
11337
TTFT (ms)
21.2
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 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 711.1 60.8 19.2 GB view
4k 797.6 57.6 20.7 GB view
8k 722.6 53.1 21.2 GB current
16k 646.5 47.6 22.3 GB view
32k 522.3 39.7 24.5 GB view