← Back to community benchmarks
gemma-4-26B-A4B-it
Performance
1k
tokens
1,276
PP tok/s
51.5
TG tok/s
803
TTFT (ms)
25.8
Peak mem (GB)
Hardware
Chip
M5 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,276 | 51.5 | 25.8 GB | current |
| 4k | 1,623 | 49.9 | 26.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 51.5 | 1.00× |
| 2× | 72.4 | 1.41× |