← Back to community benchmarks

Qwen3.5-35B-A3B-Heretic

M1 Max (24c) · 32 GB · 4bit · 2026-03-09
Performance
4k
tokens
439.0
PP tok/s
49.0
TG tok/s
9331
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 418.3 55.5 20.1 GB view
4k 439.0 49.0 20.2 GB current
Batching Results
Batch Size TG tok/s Speedup
55.5 1.00×
78.3 1.41×
93.7 1.69×