← Back to community benchmarks
gemma-4-26B-A4B-it-oQ8
Performance
32k
tokens
1,296
PP tok/s
58.8
TG tok/s
25279
TTFT (ms)
27.5
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,196 | 76.8 | 25.8 GB | view |
| 4k | 1,469 | 75.2 | 26.2 GB | view |
| 8k | 1,496 | 71.8 | 26.6 GB | view |
| 16k | 1,437 | 67.1 | 26.7 GB | view |
| 32k | 1,296 | 58.8 | 27.5 GB | current |
| 64k | 1,064 | 47.2 | 29.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 76.8 | 1.00× |
| 2× | 114.1 | 1.49× |
| 4× | 158.3 | 2.06× |