← Back to community benchmarks
gemma-4-26B-A4B9bit
Performance
1k
tokens
1,595
PP tok/s
38.4
TG tok/s
642
TTFT (ms)
28.3
Peak mem (GB)
Hardware
Chip
M5 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.3.1
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,595 | 38.4 | 28.3 GB | current |
| 4k | 1,753 | 37.9 | 28.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.4 | 1.00× |
| 2× | 49.8 | 1.30× |