← Back to community benchmarks
gemma-4-26b-a4b-it-UD
Performance
1k
tokens
667.5
PP tok/s
57.1
TG tok/s
1534
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 667.5 | 57.1 | 14.7 GB | current |
| 4k | 737.0 | 52.8 | 15.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.1 | 1.00× |
| 2× | 84.7 | 1.48× |
| 4× | 217.0 | 3.80× |