← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
586.8
PP tok/s
62.8
TG tok/s
1745
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip
M1 Ultra (48c)
Memory
128 GB
GPU Cores
48
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 586.8 | 62.8 | 16.7 GB | current |
| 4k | 684.6 | 57.9 | 17.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.8 | 1.00× |
| 2× | 87.7 | 1.40× |
| 4× | 113.7 | 1.81× |
| 8× | 135.4 | 2.16× |