← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
368.1
PP tok/s
44.7
TG tok/s
11126
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.3.8.dev3
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 343.2 | 46.9 | 14.3 GB | view |
| 4k | 368.1 | 44.7 | 14.7 GB | current |
| 8k | 378.0 | 36.7 | 14.8 GB | view |
| 16k | 367.6 | 25.4 | 15.2 GB | view |
| 32k | 342.1 | 11.5 | 16.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.9 | 1.00× |
| 2× | 60.8 | 1.30× |
| 4× | 70.9 | 1.51× |