← Back to community benchmarks
gemma-4-26B-A4B-it-oQ6
Performance
4k
tokens
3,299
PP tok/s
90.2
TG tok/s
1242
TTFT (ms)
21.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,160 | 93.6 | 20.7 GB | view |
| 4k | 3,299 | 90.2 | 21.3 GB | current |
| 8k | 3,524 | 85.7 | 21.7 GB | view |
| 16k | 3,383 | 78.9 | 22.0 GB | view |
| 32k | 3,073 | 70.9 | 22.9 GB | view |
| 64k | 2,439 | 56.8 | 24.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 93.6 | 1.00× |
| 2× | 135.2 | 1.44× |
| 4× | 191.5 | 2.05× |