← Back to community benchmarks

Nex-N2-mini

M5 Max (40c) · 128 GB · fp16 · 2026-06-05
Performance
195k
tokens
860.2
PP tok/s
32.7
TG tok/s
232493
TTFT (ms)
85.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.4.1
macOS macOS 26.5
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,830 68.7 65.6 GB view
4k 3,276 67.4 66.4 GB view
8k 3,579 65.5 66.7 GB view
16k 3,498 63.7 67.6 GB view
32k 3,049 59.5 69.1 GB view
64k 2,124 51.6 72.0 GB view
128k 1,197 38.9 78.1 GB view
195k 860.2 32.7 85.0 GB current
Batching Results
Batch Size TG tok/s Speedup
68.7 1.00×
63.2 0.92×
112.7 1.64×
124.7 1.82×