← Back to community benchmarks
gemma-4-26B-A4B-it-oQ6
Performance
16k
tokens
387.8
PP tok/s
20.9
TG tok/s
42250
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 417.0 | 40.7 | 20.0 GB | view |
| 4k | 432.2 | 38.5 | 20.4 GB | view |
| 8k | 406.8 | 29.8 | 20.6 GB | view |
| 16k | 387.8 | 20.9 | 21.0 GB | current |
| 32k | 327.3 | 13.1 | 21.8 GB | view |
| 64k | 287.0 | 7.2 | 23.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.7 | 1.00× |
| 2× | 51.2 | 1.26× |
| 4× | 55.2 | 1.36× |
| 8× | 64.9 | 1.59× |