← Back to community benchmarks
gemma-4-26B-A4B-it-uncensored-heretic-ara8bit-int8-affine
Performance
1k
tokens
1,290
PP tok/s
75.0
TG tok/s
794
TTFT (ms)
27.2
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.12
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,290 | 75.0 | 27.2 GB | current |
| 4k | 1,650 | 74.3 | 27.6 GB | view |
| 8k | 1,709 | 71.3 | 27.7 GB | view |
| 16k | 1,647 | 65.6 | 28.1 GB | view |
| 32k | 1,499 | 57.2 | 28.9 GB | view |
| 64k | 1,206 | 46.7 | 30.6 GB | view |
| 128k | 872.9 | 31.0 | 34.2 GB | view |
| 195k | 646.1 | 23.6 | 37.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 75.0 | 1.00× |
| 2× | 118.8 | 1.58× |
| 4× | 162.1 | 2.16× |
| 8× | 224.3 | 2.99× |