← Back to community benchmarks
Nemotron-Cascade-2-30B-A3B
Performance
4k
tokens
406.9
PP tok/s
59.1
TG tok/s
10068
TTFT (ms)
19.8
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.3.4
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 349.9 | 65.8 | 18.9 GB | view |
| 4k | 406.9 | 59.1 | 19.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 65.8 | 1.00× |
| 2× | 80.3 | 1.22× |
| 4× | 91.5 | 1.39× |