← Back to community benchmarks
NVIDIA-Nemotron-3-Nano-30B-A3B
Performance
32k
tokens
3,010
PP tok/s
92.1
TG tok/s
10886
TTFT (ms)
34.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.20.dev1
macOS
macOS 26.3.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,733 | 115.7 | 33.5 GB | view |
| 4k | 3,269 | 112.5 | 34.6 GB | view |
| 8k | 3,408 | 109.0 | 34.6 GB | view |
| 16k | 3,321 | 102.3 | 34.6 GB | view |
| 32k | 3,010 | 92.1 | 34.7 GB | current |
| 64k | 2,465 | 68.1 | 34.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 115.7 | 1.00× |
| 2× | 127.9 | 1.11× |
| 4× | 165.8 | 1.43× |
| 8× | 200.1 | 1.73× |