← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
601.9
PP tok/s
60.6
TG tok/s
1701
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M1 Ultra (48c)
Memory
128 GB
GPU Cores
48
Software
oMLX
v0.3.4
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 601.9 | 60.6 | 16.7 GB | current |
| 4k | 718.3 | 59.0 | 17.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 60.6 | 1.00× |
| 2× | 85.3 | 1.41× |
| 4× | 114.3 | 1.89× |
| 8× | 135.6 | 2.24× |