← Back to community benchmarks
gemma-4-26b-a4b-it-mxfp8
Performance
1k
tokens
1,007
PP tok/s
80.5
TG tok/s
1017
TTFT (ms)
25.1
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,007 | 80.5 | 25.1 GB | current |
| 4k | 1,470 | 78.4 | 25.7 GB | view |
| 8k | 1,682 | 75.5 | 25.9 GB | view |
| 16k | 1,612 | 69.9 | 26.3 GB | view |
| 32k | 1,468 | 60.2 | 27.3 GB | view |
| 64k | 1,215 | 45.7 | 29.3 GB | view |
| 128k | 879.8 | 31.2 | 33.5 GB | view |
| 195k | 665.7 | 19.9 | 38.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 80.5 | 1.00× |
| 2× | 116.7 | 1.45× |
| 4× | 148.8 | 1.85× |
| 8× | 295.8 | 3.67× |