← Back to community benchmarks
gemma-4-26b-a4b-it-5bit
Performance
8k
tokens
714.2
PP tok/s
46.9
TG tok/s
11470
TTFT (ms)
17.7
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.4
macOS
macOS 15.7.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 656.3 | 56.9 | 17.1 GB | view |
| 4k | 710.6 | 53.7 | 17.5 GB | view |
| 8k | 714.2 | 46.9 | 17.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.9 | 1.00× |
| 2× | 79.0 | 1.39× |
| 4× | 92.6 | 1.63× |
| 8× | 104.2 | 1.83× |