About the model
The 12B Gemma 4 variant — smaller and faster, a good baseline for comparing how much the larger e4b gains from extra parameters.
Capabilities
✅ Text 💻 Code
Technical specifications
| Type | ollama |
|---|---|
| Parameters | 12B |
| Quantization | Q4_K_M |
| Context window | 32768 |
Test hardware
| CPU | AMD Ryzen |
|---|---|
| GPU | NVIDIA RTX 5060 Ti 16GB |
| RAM | 32 GB DDR5 |
| OS | Ubuntu 24.04 LTS |
Test results
| Test | Run | Tokens/s | TTFT (ms) | Duration (s) | Tokens | GPU VRAM | Temp | Quality | Date |
|---|---|---|---|---|---|---|---|---|---|
| ? | #1 | 42.39 | 136 | 139.3 | 2507 | 7642 MB | 77 °C | - | 25.07.2026 |
| ? | #1 | 42.32 | 142 | 56.7 | 1919 | 7642 MB | 78 °C | - | 25.07.2026 |
| ? | #1 | 42.56 | 129 | 105.5 | 3012 | 7642 MB | 77 °C | - | 25.07.2026 |
| ? | #1 | 42.50 | 210 | 137.9 | 3549 | 7642 MB | 76 °C | - | 25.07.2026 |
| ? | #1 | 42.51 | 137 | 89.3 | 3567 | 7642 MB | 77 °C | - | 23.07.2026 |