← Back to community benchmarks

Qwen3.6-35B-A3B-Hereticmxfp8

M1 Max (32c) · 64 GB · 8bit · 2026-04-19
Performance
64k
tokens
393.7
PP tok/s
22.1
TG tok/s
166454
TTFT (ms)
40.2
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 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
64k 393.7 22.1 40.2 GB current
128k 256.1 12.3 45.5 GB view