← Back to community benchmarks
Nemotron-3-Super-120B-A12B3.6bit
Performance
16k
tokens
113.9
PP tok/s
21.1
TG tok/s
143795
TTFT (ms)
59.3
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.5.2rc1
macOS
macOS 26.5.2
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 123.7 | 23.3 | 56.1 GB | view |
| 16k | 113.9 | 21.1 | 59.3 GB | current |
| 64k | 105.1 | 18.4 | 59.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.3 | 1.00× |
| 2× | 25.5 | 1.09× |
| 4× | 51.2 | 2.20× |