← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
1,339
PP tok/s
70.1
TG tok/s
765
TTFT (ms)
14.3
Peak mem (GB)
Hardware
Chip
M5 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.3.8
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,339 | 70.1 | 14.3 GB | current |
| 4k | 1,656 | 67.1 | 14.9 GB | view |
| 64k | 1,168 | 38.0 | 17.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 70.1 | 1.00× |
| 2× | 95.5 | 1.36× |
| 4× | 121.5 | 1.73× |