← Back to community benchmarks

community--Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 6bit · 2026-03-30
Performance
1k
tokens
834.8
PP tok/s
50.9
TG tok/s
1227
TTFT (ms)
105.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.0
macOS macOS 26.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 834.8 50.9 105.3 GB current
4k 1,251 48.6 106.7 GB view
8k 1,192 45.3 107.3 GB view
Batching Results
Batch Size TG tok/s Speedup
50.9 1.00×
68.8 1.35×
78.4 1.54×