← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
878.1
PP tok/s
41.0
TG tok/s
1166
TTFT (ms)
14.2
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 878.1 | 41.0 | 14.2 GB | current |
| 4k | 933.5 | 38.1 | 14.6 GB | view |
| 8k | 1,024 | 33.0 | 14.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.0 | 1.00× |
| 2× | 60.9 | 1.49× |
| 4× | 73.0 | 1.78× |