← Back to community benchmarks

Qwen3.5-35B-A3B

M5 Max (40c) · 128 GB · bf16 · 2026-03-21
Performance
4k
tokens
2,379
PP tok/s
56.3
TG tok/s
1722
TTFT (ms)
67.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.20.dev2
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,472 57.8 66.5 GB view
4k 2,379 56.3 67.3 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 57.8 1.00×
2× 78.0 1.35×
4× 118.9 2.06×