← Back to community benchmarks

Qwen3.5-122B-A10B-oQ2

M1 Max (32c) · 64 GB · 2bit · 2026-04-05
Performance
1k
tokens
168.2
PP tok/s
27.5
TG tok/s
6089
TTFT (ms)
41.3
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.4
macOS macOS 15.7.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 168.2 27.5 41.3 GB current
4k 148.0 22.9 42.6 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 27.5 1.00×
2× 35.4 1.29×
4× 35.0 1.27×