← Back to community benchmarks
gemma-4-26B-A4B-it-oQ8
Performance
32k
tokens
2,821
PP tok/s
61.9
TG tok/s
11614
TTFT (ms)
30.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.2.dev3
macOS
macOS 26.6
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,622 | 76.5 | 27.9 GB | view |
| 4k | 3,203 | 61.9 | 28.5 GB | view |
| 8k | 3,289 | 72.2 | 28.7 GB | view |
| 16k | 3,221 | 67.5 | 29.2 GB | view |
| 32k | 2,821 | 61.9 | 30.1 GB | current |
| 64k | 2,289 | 48.2 | 32.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 76.5 | 1.00× |
| 2× | 117.9 | 1.54× |
| 4× | 164.4 | 2.15× |