← Back to community benchmarks

Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated-MTPLX

M5 Max (40c) · 128 GB · 4bit · 2026-06-07
Performance
16k
tokens
1,296
PP tok/s
46.7
TG tok/s
12638
TTFT (ms)
69.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.4.1
macOS macOS 26.5.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 921.6 52.0 65.6 GB view
4k 1,465 51.6 66.9 GB view
8k 1,415 48.5 67.8 GB view
16k 1,296 46.7 69.0 GB current
32k 1,044 39.0 71.6 GB view
64k 771.8 34.4 76.9 GB view
Batching Results
Batch Size TG tok/s Speedup
52.0 1.00×
81.9 1.58×
109.6 2.11×