← Back to community benchmarks

Qwen3.5-122B-A10B-Text-mxfp4

M5 Max (40c) · 128 GB · 4bit · 2026-04-12
Performance
4k
tokens
1,449
PP tok/s
61.8
TG tok/s
2826
TTFT (ms)
63.4
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.4
macOS macOS 26.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,045 61.5 62.0 GB view
4k 1,449 61.8 63.4 GB current
8k 1,319 58.3 64.0 GB view
16k 1,151 52.1 65.1 GB view
Batching Results
Batch Size TG tok/s Speedup
61.5 1.00×
94.9 1.54×
118.2 1.92×