← Back to community benchmarks

Qwen3.5-35B-A3B-Hereticmxfp8

M1 Ultra (64c) · 64 GB · 8bit · 2026-03-12
Performance
16k
tokens
1,041
PP tok/s
43.0
TG tok/s
15741
TTFT (ms)
35.7
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 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 1,041 43.0 35.7 GB current
32k 942.4 33.6 36.5 GB view
64k 712.3 22.4 38.2 GB view