← Back to community benchmarks

Qwen3.5-35B-A3B

M3 Max (40c) · 128 GB · 8bit · 2026-03-10
Performance
1k
tokens
1,024
PP tok/s
46.3
TG tok/s
1000
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,024 46.3 36.2 GB current
4k 1,125 46.2 36.3 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 46.3 1.00×
2× 83.2 1.80×
4× 126.8 2.74×
8× 119.8 2.59×