FU

Home FunctionGemma 270m

FunctiongemmaGGUF by acon96Updated 2025-12-22
Download on Hugging Face
Parameters268M
Context—
Layers—
Architecture—
Smallest quant0.0 GB
Quick answer

Home FunctionGemma 270m needs about 0.8 GB of memory at Q3_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 10 quants, from 0.0 GB to 0.5 GB (BF16).

Fine‑tuned FunctionGemma for home device control

Home FunctionGemma 270m is a 0.268 billion‑parameter model fine‑tuned from google/functiongemma-270m-it. It controls home devices via the Assist API and answers questions about the home state. The model is quantized for low‑resource environments.

Good at

  • Home device control
  • Basic QA about home state
  • Runs on Raspberry Pi

Limits

  • No vision support
  • Small context length
  • Requires 8 k context for estimates

Best for

  • Home automation scripts
  • Assistant integration
  • Low‑resource local inference

Who it’s for. Developers building home automation assistants who need a lightweight, function‑aware LLM. The model is suitable for embedded systems and local deployments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
IQ4_XS0.2 GB 0.8 GB
Fits Get file →
Q4_00.2 GB 0.8 GB
Fits Get file →
IQ4_NL0.2 GB 0.8 GB
Fits Get file →
Q3_K_M0.2 GB 0.8 GB
Fits Get file →
Q4_10.2 GB 0.8 GB
Fits Get file →
Q5_K_M0.3 GB 0.8 GB
Fits Get file →
Q6_K0.3 GB 0.8 GB
Fits Get file →
Q8_00.3 GB 0.8 GB
Fits Get file →
BF160.5 GB 1.1 GB
Fits Get file →

For 8 GB VRAM, use IQ4_XS, Q4_0, or Q3_K_M (0.24 GB file, ~0.8 GB memory). For 16 GB VRAM, Q5_K_M or Q6_K (0.26–0.28 GB file, ~0.8 GB memory). For higher precision, BF16 (0.54 GB file, ~1.1 GB memory). Estimates are approximate.

What GPU do you need for Home FunctionGemma 270m?

These figures add the file size, an fp16 KV cache at an 8K context window 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 BF16 (0.5 GB file, about 1.1 GB in use).

Which Home FunctionGemma 270m quant should you choose?

Q3_K_M (0.2 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters268M

Source

Quantized byacon96
Licensegemma
Downloads (HF)1,899
Last updated2025-12-22

Frequently asked questions about Home FunctionGemma 270m

How much VRAM does Home FunctionGemma 270m need?

About 0.8 GB at Q3_K_M with an 8K context window. That is the 0.2 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 Home FunctionGemma 270m on an 8 GB GPU?

Yes, with BF16: the 0.5 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Home FunctionGemma 270m GGUF?

It depends on the quant: file is 0.0 GB, IQ4_XS is 0.2 GB, Q4_0 is 0.2 GB, IQ4_NL is 0.2 GB, Q3_K_M is 0.2 GB, Q4_1 is 0.2 GB and 4 more.

Where can I download Home FunctionGemma 270m GGUF?

The files are on Hugging Face in the acon96/Home-FunctionGemma-270m repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Home FunctionGemma 270m use?

Hugging Face lists the license as gemma. 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 Home FunctionGemma 270m on 8 GB VRAM?

Yes, quantizations like IQ4_XS, Q4_0, or Q3_K_M fit within 8 GB VRAM with ~0.8 GB memory usage.

Does the model support image inputs?

No, the model has no vision capabilities.

What context length does it support?

It is trained for 8 k context tokens; larger contexts are not supported.

Other GGUFs of functiongemma-270m-it

Similar models

Browse all →

More from acon96

All by acon96 →

More Functiongemma models

All Functiongemma →

Other tiny models

All tiny models →