← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 128 GB · bf16 · 2026-04-18
Performance
4k
tokens
1,751
PP tok/s
60.1
TG tok/s
2339
TTFT (ms)
66.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.4
macOS macOS 15.7.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,247 61.7 65.6 GB view
4k 1,751 60.1 66.4 GB current
Batching Results
Batch Size TG tok/s Speedup
61.7 1.00×
60.2 0.98×
105.8 1.71×
86.1 1.40×