← Back to community benchmarks
gemma-4-26b-a4b-it-mxfp8
Performance
4k
tokens
697.1
PP tok/s
43.6
TG tok/s
5876
TTFT (ms)
25.4
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.4
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 642.3 | 45.4 | 25.0 GB | view |
| 4k | 697.1 | 43.6 | 25.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.4 | 1.00× |
| 2× | 60.7 | 1.34× |
| 4× | 68.7 | 1.51× |
| 8× | 77.0 | 1.70× |