← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 128 GB · 8bit · 2026-05-01
Performance
1k
tokens
1,182
PP tok/s
85.3
TG tok/s
866
TTFT (ms)
35.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 15.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,182 85.3 35.4 GB current
4k 1,663 82.3 36.2 GB view
Batching Results
Batch Size TG tok/s Speedup
85.3 1.00×
137.1 1.61×
341.0 4.00×