self-hosted/ai
§01·model · /models

Llama 3.2 1B

llmactiveLlama 3.2 Community License

1B instruction-tuned LLM by Meta (Llama 3.2), sized for edge and on-device use. Llama 3.2 Community License.

§02·GPUs that run this model
1 total
GPUVRAMSeriesBest speedMin VRAMWorksBenchmarksRecipe
RX 7900 XTX24GBamd106tokens/s24GB1recipecheck ↗

benchmarked·~ runs via recipe (not benchmarked)· untested·doesn't fit