← Back to community benchmarks
gemma-4-26b
Performance
32k
tokens
416.0
PP tok/s
27.9
TG tok/s
78767
TTFT (ms)
16.0
Peak mem (GB)
Hardware
Chip
M3 Pro (18c)
Memory
36 GB
GPU Cores
18
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 433.8 | 42.2 | 14.3 GB | view |
| 4k | 503.6 | 40.1 | 14.9 GB | view |
| 8k | 517.4 | 38.6 | 15.1 GB | view |
| 16k | 484.5 | 29.8 | 15.2 GB | view |
| 32k | 416.0 | 27.9 | 16.0 GB | current |
| 64k | 338.7 | 21.2 | 17.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 42.2 | 1.00× |
| 2× | 61.1 | 1.45× |
| 4× | 69.7 | 1.65× |
| 8× | 84.1 | 1.99× |