← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
1,028
PP tok/s
36.5
TG tok/s
3986
TTFT (ms)
48.2
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 871.5 | 38.1 | 47.7 GB | view |
| 4k | 1,028 | 36.5 | 48.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.1 | 1.00× |
| 2× | 32.3 | 0.85× |
| 4× | 57.1 | 1.50× |