← Back to community benchmarks
supergemma4-26b-uncensored4bit-v2
Performance
4k
tokens
711.9
PP tok/s
67.0
TG tok/s
5754
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 662.2 | 71.7 | 14.0 GB | view |
| 4k | 711.9 | 67.0 | 14.7 GB | current |
| 8k | 728.6 | 65.6 | 14.8 GB | view |
| 16k | 704.2 | 58.1 | 15.3 GB | view |
| 32k | 622.9 | 50.7 | 16.2 GB | view |
| 64k | 523.3 | 39.2 | 18.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 71.7 | 1.00× |
| 2× | 94.7 | 1.32× |
| 4× | 120.7 | 1.68× |