← Back to community benchmarks

Qwen3.6-35B-A3B-Hereticmxfp8

M3 Ultra (80c) · 512 GB · 8bit · 2026-04-28
Performance
4k
tokens
907.6
PP tok/s
78.4
TG tok/s
4513
TTFT (ms)
35.2
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.6
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,142 321.0 35.7 GB view
4k 907.6 78.4 35.2 GB current
8k 2,602 74.9 35.5 GB view