← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
372.1
PP tok/s
44.5
TG tok/s
11007
TTFT (ms)
17.1
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
64 GB
GPU Cores
24
Software
oMLX
v0.3.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 342.6 | 47.8 | 16.7 GB | view |
| 4k | 372.1 | 44.5 | 17.1 GB | current |
| 8k | 373.9 | 38.3 | 17.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.8 | 1.00× |
| 2× | 58.9 | 1.23× |