← Back to community benchmarks
gemma-4-31b-it-uncensored-heretic-ara4bit-mixed_4_6
Performance
1k
tokens
72.9
PP tok/s
13.5
TG tok/s
14043
TTFT (ms)
18.9
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 72.9 | 13.5 | 18.9 GB | current |
| 4k | 72.9 | 12.2 | 21.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 13.5 | 1.00× |
| 2× | 15.4 | 1.14× |
| 4× | 16.1 | 1.19× |