← Back to community benchmarks
gemma-4-26B-A4B-it-5bit-DWQ
Performance
16k
tokens
261.4
PP tok/s
21.8
TG tok/s
62672
TTFT (ms)
17.9
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 254.5 | 34.7 | 16.9 GB | view |
| 4k | 269.9 | 32.6 | 17.4 GB | view |
| 8k | 269.1 | 27.5 | 17.5 GB | view |
| 16k | 261.4 | 21.8 | 17.9 GB | current |
| 32k | 244.8 | 11.7 | 18.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.7 | 1.00× |
| 2× | 40.2 | 1.16× |
| 4× | 44.0 | 1.27× |
| 8× | 49.7 | 1.43× |