← Back to community benchmarks
NVIDIA-Nemotron-3-Nano-30B-A3B
Performance
1k
tokens
1,185
PP tok/s
151.3
TG tok/s
864
TTFT (ms)
18.9
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,185 | 151.3 | 18.9 GB | current |
| 4k | 1,530 | 143.7 | 19.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 151.3 | 1.00× |
| 2× | 216.6 | 1.43× |
| 4× | 270.0 | 1.78× |
| 8× | 316.9 | 2.09× |