← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
932.5
PP tok/s
67.3
TG tok/s
4393
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 817.2 | 70.7 | 14.2 GB | view |
| 4k | 932.5 | 67.3 | 14.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 70.7 | 1.00× |
| 2× | 105.9 | 1.50× |
| 4× | 134.5 | 1.90× |