← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
421.8
PP tok/s
53.1
TG tok/s
2428
TTFT (ms)
14.2
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.3
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 421.8 | 53.1 | 14.2 GB | current |
| 4k | 486.3 | 49.6 | 14.7 GB | view |
| 8k | 494.0 | 41.0 | 14.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 53.1 | 1.00× |
| 2× | 71.9 | 1.35× |
| 4× | 87.4 | 1.65× |