← Back to community benchmarks
gemma-4-26B-A4B-it-oQ3
Performance
32k
tokens
283.4
PP tok/s
25.3
TG tok/s
115610
TTFT (ms)
13.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.3.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 359.0 | 38.0 | 11.4 GB | view |
| 4k | 360.7 | 36.0 | 12.1 GB | view |
| 8k | 341.3 | 33.1 | 12.2 GB | view |
| 16k | 305.4 | 30.3 | 12.7 GB | view |
| 32k | 283.4 | 25.3 | 13.6 GB | current |
| 64k | 232.9 | 16.7 | 14.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.0 | 1.00× |
| 2× | 73.3 | 1.93× |