← Back to community benchmarks
gemma-4-26b-a4b-it-oQ4
Performance
64k
tokens
392.0
PP tok/s
9.8
TG tok/s
167204
TTFT (ms)
19.0
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.2
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 480.3 | 37.4 | 15.5 GB | view |
| 4k | 496.8 | 34.3 | 15.8 GB | view |
| 8k | 495.6 | 31.0 | 16.1 GB | view |
| 16k | 480.1 | 25.3 | 16.5 GB | view |
| 32k | 449.5 | 18.9 | 17.3 GB | view |
| 64k | 392.0 | 9.8 | 19.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.4 | 1.00× |
| 2× | 48.6 | 1.30× |
| 4× | 66.9 | 1.79× |
| 8× | 81.8 | 2.19× |