← Back to community benchmarks
gemma-4-31B-it-uncensored-heretic
Performance
1k
tokens
158.7
PP tok/s
18.5
TG tok/s
6451
TTFT (ms)
17.8
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.4.4rc1
macOS
macOS 27.0
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 158.7 | 18.5 | 17.8 GB | current |
| 4k | 110.6 | 17.6 | 19.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.5 | 1.00× |
| 2× | 25.0 | 1.35× |
| 4× | 26.9 | 1.45× |