§01·model · /models
stablelm2 12b
llmactiveStability AI Community License
12B multilingual LLM by Stability AI, the StableLM 2 generation. One recipe covers it, on an 8 GB RTX 3060 Ti at 18.73 tokens/s in the shared 4-bit Ollama run — second-slowest of the eleven models measured on that card, which is roughly what a 12B on 8 GB looks like. Stability AI Community License.
§02·GPUs that run this model
1 total| GPU | VRAM | Series | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|---|---|
| RTX 3060 Ti | 8GB | 30 | 18.73tokens/s | 8GB | ✓ | 1benchrecipe | check ↗ |
✓ benchmarked·~ runs via recipe (not benchmarked)·— untested·✕doesn't fit