← Back to community benchmarks
gemma-4-26B-A4B-it-uncensored-abliterix4bit
Performance
4k
tokens
933.2
PP tok/s
68.7
TG tok/s
4389
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip
M2 Ultra (60c)
Memory
192 GB
GPU Cores
60
Software
oMLX
v0.3.8rc1
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 807.4 | 72.7 | 14.3 GB | view |
| 4k | 933.2 | 68.7 | 14.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 72.7 | 1.00× |
| 2× | 108.3 | 1.49× |
| 4× | 142.0 | 1.95× |