← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Max (40c) · 128 GB · 8bit · 2026-04-16
Performance
32k
tokens
1,344
PP tok/s
61.3
TG tok/s
24373
TTFT (ms)
38.5
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 1,344 61.3 38.5 GB current
64k 1,025 43.9 41.2 GB view