← Back to community benchmarks

Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ4e

M2 Max (38c) · 32 GB · 4bit · 2026-05-12
Performance
4k
tokens
755.4
PP tok/s
73.6
TG tok/s
5422
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 32 GB
GPU Cores 38
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 554.2 77.7 19.9 GB view
4k 755.4 73.6 20.7 GB current
Batching Results
Batch Size TG tok/s Speedup
77.7 1.00×
111.9 1.44×
142.1 1.83×