← Back to community benchmarks

Qwen3.5-35B-A3B-Hereticmxfp8

M4 Pro (20c) · 64 GB · 8bit · 2026-03-12
Performance
4k
tokens
842.7
PP tok/s
56.3
TG tok/s
4861
TTFT (ms)
34.5
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.2.8
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 749.0 58.5 34.4 GB view
4k 842.7 56.3 34.5 GB current
8k 830.3 53.5 34.7 GB view
16k 776.3 48.6 35.1 GB view
32k 647.9 41.4 36.0 GB view
64k 514.5 28.5 37.6 GB view
Batching Results
Batch Size TG tok/s Speedup
58.5 1.00×
81.4 1.39×
94.1 1.61×
106.8 1.83×