← Back to community benchmarks

Qwen3.5-122B-A10B-5bit

M5 Max (40c) · 128 GB · 5bit · 2026-04-16
Performance
32k
tokens
1,076
PP tok/s
37.9
TG tok/s
30455
TTFT (ms)
85.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 864.7 56.9 79.8 GB view
4k 1,427 54.4 81.1 GB view
8k 1,414 52.5 81.7 GB view
16k 1,307 45.5 82.9 GB view
32k 1,076 37.9 85.3 GB current
Batching Results
Batch Size TG tok/s Speedup
56.9 1.00×
83.4 1.47×
105.0 1.85×
114.7 2.02×