← Back to community benchmarks
community--NVIDIA-Nemotron-3-Nano-30B-A3B
Performance
16k
tokens
3,306
PP tok/s
102.1
TG tok/s
4956
TTFT (ms)
34.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.2.dev2
macOS
macOS 26.5.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,554 | 111.6 | 33.5 GB | view |
| 4k | 2,863 | 108.4 | 34.6 GB | view |
| 8k | 3,644 | 104.1 | 34.6 GB | view |
| 16k | 3,306 | 102.1 | 34.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 111.6 | 1.00× |
| 2× | 139.3 | 1.25× |
| 4× | 181.8 | 1.63× |
| 8× | 213.6 | 1.91× |