← Back to community benchmarks

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

M1 Ultra (64c) · 128 GB · 4bit · 2026-03-11
Performance
4k
tokens
341.7
PP tok/s
31.0
TG tok/s
11988
TTFT (ms)
62.3
Peak mem (GB)
Hardware
Chip M1 Ultra (64c)
Memory 128 GB
GPU Cores 64
Software
oMLX v0.2.7
macOS macOS 26.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 302.1 31.9 62.0 GB view
4k 341.7 31.0 62.3 GB current
8k 344.0 28.8 62.6 GB view
Batching Results
Batch Size TG tok/s Speedup
31.9 1.00×
51.7 1.62×
71.2 2.23×