← Back to community benchmarks

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

M1 Max (32c) · 64 GB · 6bit · 2026-04-05
Performance
1k
tokens
463.6
PP tok/s
53.0
TG tok/s
2209
TTFT (ms)
27.3
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.0
macOS macOS 26.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 463.6 53.0 27.3 GB current
4k 571.4 50.2 28.3 GB view
8k 572.7 47.1 28.6 GB view
16k 553.4 42.5 29.3 GB view
32k 506.0 35.4 30.6 GB view
64k 406.9 26.0 33.2 GB view
Batching Results
Batch Size TG tok/s Speedup
53.0 1.00×
73.1 1.38×
90.6 1.71×