← Back to community benchmarks

Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled

M3 Max (40c) · 128 GB · 8bit · 2026-03-19
Performance
8k
tokens
1,416
PP tok/s
64.1
TG tok/s
5786
TTFT (ms)
36.6
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.19
macOS macOS 15.7.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,098 71.2 35.4 GB view
4k 1,415 68.6 36.3 GB view
8k 1,416 64.1 36.6 GB current
16k 1,334 52.6 37.3 GB view
Batching Results
Batch Size TG tok/s Speedup
71.2 1.00×
114.2 1.60×
163.5 2.30×
217.4 3.05×