← Back to community benchmarks

Qwen3.6-35B-A3B-Hereticmxfp8

M1 Max (32c) · 64 GB · 8bit · 2026-04-19
Performance
128k
tokens
256.1
PP tok/s
12.3
TG tok/s
511785
TTFT (ms)
45.5
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
64k 393.7 22.1 40.2 GB view
128k 256.1 12.3 45.5 GB current