← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
8k
tokens
496.1
PP tok/s
38.1
TG tok/s
16514
TTFT (ms)
14.8
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 432.4 | 42.1 | 14.2 GB | view |
| 4k | 484.9 | 45.0 | 14.7 GB | view |
| 8k | 496.1 | 38.1 | 14.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 42.1 | 1.00× |
| 2× | 68.5 | 1.63× |