← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
64k
tokens
944.5
PP tok/s
39.1
TG tok/s
69389
TTFT (ms)
17.0
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
192 GB
GPU Cores
76
Software
oMLX
v0.3.8
macOS
macOS 26.4
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 988.3 | 86.6 | 13.6 GB | view |
| 4k | 1,175 | 82.1 | 14.2 GB | view |
| 8k | 1,217 | 77.0 | 14.4 GB | view |
| 16k | 1,197 | 67.5 | 14.8 GB | view |
| 32k | 1,124 | 54.9 | 15.8 GB | view |
| 64k | 944.5 | 39.1 | 17.0 GB | current |
| 128k | 645.0 | 24.6 | 20.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 86.6 | 1.00× |
| 2× | 127.2 | 1.47× |
| 4× | 173.1 | 2.00× |
| 8× | 216.2 | 2.50× |