← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
8k
tokens
910.7
PP tok/s
32.6
TG tok/s
8996
TTFT (ms)
14.0
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 740.1 | 43.0 | 13.5 GB | view |
| 4k | 880.8 | 39.6 | 13.9 GB | view |
| 8k | 910.7 | 32.6 | 14.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 43.0 | 1.00× |
| 2× | 59.6 | 1.39× |
| 4× | 67.4 | 1.57× |