← Back to community benchmarks
Nemotron-3-Nano-30B-A3B-TurboQuant
Performance
64k
tokens
4,323
PP tok/s
63.8
TG tok/s
15161
TTFT (ms)
35.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,411 | 67.5 | 34.1 GB | view |
| 4k | 1,871 | 65.7 | 35.3 GB | view |
| 8k | 1,897 | 64.8 | 35.3 GB | view |
| 16k | 4,760 | 66.7 | 35.1 GB | view |
| 32k | 4,666 | 65.9 | 35.2 GB | view |
| 64k | 4,323 | 63.8 | 35.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 67.5 | 1.00× |
| 2× | 89.5 | 1.33× |
| 4× | 111.2 | 1.65× |
| 8× | 125.7 | 1.86× |