← Back to community benchmarks

Qwen3.5-35B-A3B

M3 Max (30c) · 96 GB · 4bit · 2026-03-10
Performance
4k
tokens
734.3
PP tok/s
57.7
TG tok/s
5578
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 96 GB
GPU Cores 30
Software
oMLX v0.2.7
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 703.9 60.9 20.0 GB view
4k 734.3 57.7 20.2 GB current
Batching Results
Batch Size TG tok/s Speedup
60.9 1.00×
86.5 1.42×
95.1 1.56×