← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
3,302
PP tok/s
75.3
TG tok/s
310
TTFT (ms)
15.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.1
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,302 | 75.3 | 15.3 GB | current |
| 4k | 3,857 | 72.3 | 15.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 75.3 | 1.00× |
| 2× | 73.0 | 0.97× |
| 4× | 124.2 | 1.65× |