← Back to community benchmarks
nightmedia--gemma-4-26B-A4B-it-mxfp4
Performance
8k
tokens
359.5
PP tok/s
26.3
TG tok/s
22788
TTFT (ms)
14.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.1
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 379.3 | 31.6 | 14.3 GB | view |
| 4k | 371.7 | 27.6 | 14.7 GB | view |
| 8k | 359.5 | 26.3 | 14.8 GB | current |
| 16k | 330.2 | 21.0 | 15.2 GB | view |
| 32k | 284.1 | 10.0 | 16.0 GB | view |
| 64k | 223.6 | 3.4 | 17.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 31.6 | 1.00× |
| 2× | 38.0 | 1.20× |