← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
64k
tokens
1,019
PP tok/s
34.3
TG tok/s
64323
TTFT (ms)
29.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,206 | 77.7 | 25.7 GB | view |
| 4k | 1,389 | 73.4 | 26.2 GB | view |
| 64k | 1,019 | 34.3 | 29.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 77.7 | 1.00× |
| 2× | 116.9 | 1.50× |
| 4× | 157.9 | 2.03× |
| 8× | 200.8 | 2.58× |