← Back to community benchmarks

Qwen3.5-35B-A3B

M3 Max (30c) · 96 GB · 4bit · 2026-03-13
Performance
1k
tokens
1,137
PP tok/s
85.9
TG tok/s
901
TTFT (ms)
20.1
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 96 GB
GPU Cores 30
Software
oMLX v0.2.8
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,137 85.9 20.1 GB current
4k 1,154 74.8 20.2 GB view
Batching Results
Batch Size TG tok/s Speedup
85.9 1.00×
133.1 1.55×
155.5 1.81×