← Back to community benchmarks

DeepSeek-V3.2

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-12
Performance
16k
tokens
128.0
PP tok/s
14.1
TG tok/s
128002
TTFT (ms)
367.3
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.9
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 209.8 19.3 354.2 GB view
4k 201.0 15.8 356.6 GB view
8k 169.7 15.1 360.1 GB view
16k 128.0 14.1 367.3 GB current
32k 84.0 12.8 382.2 GB view
Batching Results
Batch Size TG tok/s Speedup
19.3 1.00×
26.4 1.37×