← Back to community benchmarks

Qwen3.5-35B-A3B-Hereticmxfp8

M1 Ultra (64c) · 64 GB · 8bit · 2026-03-12
Performance
32k
tokens
942.4
PP tok/s
33.6
TG tok/s
34770
TTFT (ms)
36.5
Peak mem (GB)
Hardware
Chip M1 Ultra (64c)
Memory 64 GB
GPU Cores 64
Software
oMLX v0.2.9
macOS macOS 26.3.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 1,041 43.0 35.7 GB view
32k 942.4 33.6 36.5 GB current
64k 712.3 22.4 38.2 GB view