← Back to community benchmarks
gemma-4-26b-a4b-it-UD
Performance
16k
tokens
3,421
PP tok/s
88.7
TG tok/s
4789
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,110 | 104.7 | 15.2 GB | view |
| 4k | 3,322 | 99.5 | 15.7 GB | view |
| 8k | 3,660 | 95.9 | 16.4 GB | view |
| 16k | 3,421 | 88.7 | 16.6 GB | current |
| 32k | 3,141 | 77.0 | 17.4 GB | view |
| 64k | 2,505 | 60.8 | 19.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 104.7 | 1.00× |
| 2× | 151.9 | 1.45× |
| 4× | 213.6 | 2.04× |