← Back to community benchmarks

Qwen3.5-35B-A3B-Claude-4.6-Opus-Engineer-9e-qx64-hi

M1 Max (24c) · 64 GB · 6bit · 2026-03-12
Performance
4k
tokens
399.6
PP tok/s
48.2
TG tok/s
10251
TTFT (ms)
25.4
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.2.9
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 352.3 51.4 25.2 GB view
4k 399.6 48.2 25.4 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 51.4 1.00×
2× 67.0 1.30×
4× 79.6 1.55×