distil home assistant functiongemma needs about 3.8 GB of memory at its main file (a 2.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Distil-Home-Assistant-FunctionGemma: on-device smart home intent classification
Distil-Home-Assistant-FunctionGemma is a fine‑tuned FunctionGemma model for multi‑turn intent classification and slot extraction in smart home controllers. It delivers 96.71% tool call accuracy while running locally for private, low‑latency control.
Good at
- Multi‑turn smart home intent classification
- Tool call accuracy 96.71%
- On‑device privacy
Limits
- Trained only on English smart home intents
- Supports only 6 smart home functions
- Temperature range fixed to 60-80°F
Best for
- On‑device smart home controllers
- Text‑based smart home chatbots
- Edge deployment for local hubs
Who it’s for. Developers building privacy‑first smart home systems that require reliable, low‑latency intent classification and structured tool calls. The model is ideal for edge devices with limited resources.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.4 GB | 3.8 GB | Fits | Get file → |
The available GGUF file is 2.39 GB with an estimated memory usage of 3.8 GB at 8 k context. This is suitable for systems with at least 4 GB VRAM. No other quantized variants are provided.
What GPU do you need for distil home assistant functiongemma?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (2.4 GB file, about 3.8 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about distil home assistant functiongemma
How much VRAM does distil home assistant functiongemma need?
About 3.8 GB at its main file with an 8K context window. That is the 2.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run distil home assistant functiongemma on an 8 GB GPU?
Yes, with the smaller files: the 2.4 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of distil home assistant functiongemma GGUF?
It depends on the quant: file is 2.4 GB.
What context length does distil home assistant functiongemma support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download distil home assistant functiongemma GGUF?
The files are on Hugging Face in the distil-labs/distil-home-assistant-functiongemma repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does distil home assistant functiongemma use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 4 GB VRAM?
Yes, the 2.39 GB GGUF file requires approximately 3.8 GB of VRAM at 8 k context, fitting within a 4 GB budget.
Does the model support non‑English intents?
No, it was trained only on English smart home intents.
What functions can it call?
It handles six specific smart home operations defined in its training data.