← Back to community benchmarks

rnj-1-instruct

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-14
Performance
8k
tokens
1,013
PP tok/s
41.9
TG tok/s
8092
TTFT (ms)
12.0
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.11
macOS macOS 26.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,027 56.6 10.0 GB view
4k 1,094 50.1 10.9 GB view
8k 1,013 41.9 12.0 GB current
16k 869.6 31.3 13.9 GB view
32k 665.2 22.4 17.9 GB view
Batching Results
Batch Size TG tok/s Speedup
56.6 1.00×
99.1 1.75×
148.2 2.62×
184.5 3.26×