← Back to community benchmarks
gemma-4-26B-A4B-it-uncensored-oQ8
Performance
8k
tokens
706.4
PP tok/s
42.2
TG tok/s
11596
TTFT (ms)
26.6
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.8
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 674.7 | 45.0 | 25.8 GB | view |
| 4k | 723.7 | 44.1 | 26.4 GB | view |
| 8k | 706.4 | 42.2 | 26.6 GB | current |
| 16k | 619.0 | 37.1 | 27.1 GB | view |
| 32k | 561.4 | 32.4 | 27.5 GB | view |
| 64k | 480.5 | 12.2 | 29.2 GB | view |
| 128k | 360.8 | 1.1 | 32.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.0 | 1.00× |
| 2× | 65.0 | 1.44× |