← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
1,773
PP tok/s
50.3
TG tok/s
2311
TTFT (ms)
26.2
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,212 | 52.6 | 25.7 GB | view |
| 4k | 1,773 | 50.3 | 26.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 52.6 | 1.00× |
| 2× | 105.1 | 2.00× |
| 4× | 200.1 | 3.80× |