← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
326.4
PP tok/s
27.4
TG tok/s
12550
TTFT (ms)
15.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.2
macOS
macOS 15.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 344.2 | 29.3 | 15.3 GB | view |
| 4k | 326.4 | 27.4 | 15.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.3 | 1.00× |
| 2× | 40.0 | 1.37× |
| 4× | 45.2 | 1.54× |