← Back to community benchmarks
gemma-4-26B-A4B-it-oQ8
Performance
32k
tokens
3,067
PP tok/s
67.7
TG tok/s
10683
TTFT (ms)
29.6
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.10
macOS
macOS 26.5
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,008 | 87.3 | 27.9 GB | view |
| 4k | 3,251 | 84.2 | 28.2 GB | view |
| 8k | 3,510 | 81.3 | 28.4 GB | view |
| 16k | 3,419 | 76.0 | 28.8 GB | view |
| 32k | 3,067 | 67.7 | 29.6 GB | current |
| 64k | 2,496 | 54.8 | 31.3 GB | view |
| 128k | 1,729 | 40.2 | 34.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 87.3 | 1.00× |
| 2× | 128.1 | 1.47× |
| 4× | 178.6 | 2.05× |