← Back to community benchmarks
NVIDIA-Nemotron-3-Nano-30B-A3B
Performance
1k
tokens
1,062
PP tok/s
81.6
TG tok/s
965
TTFT (ms)
33.5
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.18
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,062 | 81.6 | 33.5 GB | current |
| 4k | 1,253 | 78.9 | 34.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 81.6 | 1.00× |
| 2× | 124.9 | 1.53× |
| 4× | 157.3 | 1.93× |