← Back to community benchmarks
supergemma
Performance
4k
tokens
912.6
PP tok/s
75.8
TG tok/s
4488
TTFT (ms)
14.4
Peak mem (GB)
Hardware
Chip
M2 Ultra (60c)
Memory
128 GB
GPU Cores
60
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 773.2 | 80.8 | 14.0 GB | view |
| 4k | 912.6 | 75.8 | 14.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 80.8 | 1.00× |
| 2× | 113.5 | 1.40× |
| 4× | 148.8 | 1.84× |