← 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
8k
tokens
1,091
PP tok/s
51.9
TG tok/s
7510
TTFT (ms)
67.8
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 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 771.4 56.6 65.6 GB view
4k 993.5 55.5 66.9 GB view
8k 1,091 51.9 67.8 GB current
16k 1,077 49.6 69.0 GB view
Batching Results
Batch Size TG tok/s Speedup
56.6 1.00×
85.8 1.52×
109.9 1.94×