← Back to community benchmarks

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

M2 Ultra (60c) · 64 GB · 4bit · 2026-03-12
Performance
4k
tokens
1,005
PP tok/s
79.3
TG tok/s
4077
TTFT (ms)
19.4
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 64 GB
GPU Cores 60
Software
oMLX v0.2.9
macOS macOS 15.7.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 646.5 82.6 19.2 GB view
4k 1,005 79.3 19.4 GB current
8k 1,078 72.8 19.6 GB view
16k 1,042 59.4 20.0 GB view
32k 954.1 38.1 20.8 GB view
64k 789.0 23.6 22.5 GB view
Batching Results
Batch Size TG tok/s Speedup
82.6 1.00×
137.7 1.67×
191.1 2.31×