HO

Home 3B v3

HomeGGUF by acon96Updated 2025-10-25
Download on Hugging Face
Parameters2.8B
Context4K
Layers32
Architecturestablelm
Smallest quant1.1 GB
Quick answer

Home 3B v3 needs about 4.9 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 1.1 GB (Q2_K) to 5.6 GB (F16).

Home 3B v3 – a StableLM‑based model for Home Assistant control

Home 3B v3 is a fine‑tuned StableLM‑3B‑Zephyr model designed for Home Assistant function calling. It supports basic multi‑personality, multi‑language, and device control. The model is quantized with llama.cpp for low‑resource deployment.

Good at

  • Home Assistant device control
  • Basic question answering
  • Function calling in English, German, Spanish, French

Limits

  • No vision support
  • Limited to 4096 context tokens
  • License type is other

Best for

  • Raspberry Pi Home Assistant setups
  • Low‑memory edge devices
  • In‑house automation scripts

Who it’s for. Developers building Home Assistant integrations who need a lightweight LLM that can call services and answer user queries. The model is suitable for users who prefer a small footprint and do not require vision or large context.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.1 GB 2.9 GB
Fits Get file →
Q2_K1.1 GB 2.9 GB
Fits Get file →
Q3_K_M1.4 GB 3.2 GB
Fits Get file →
Q3_K_M1.4 GB 3.2 GB
Fits Get file →
Q4_K_M1.7 GB 3.6 GB
Fits Get file →
Q4_K_M1.7 GB 3.6 GB
Fits Get file →
Q5_K_M2.0 GB 3.8 GB
Fits Get file →
Q5_K_M2.0 GB 3.8 GB
Fits Get file →
Q8_03.0 GB 4.8 GB
Fits Get file →
Q8_03.0 GB 4.8 GB
Fits Get file →
F165.6 GB 7.4 GB
Tight Get file →
F165.6 GB 7.4 GB
Tight Get file →

For 8 GB VRAM, Q2_K (1.08 GB, 4.3 GB memory at 8k context) is recommended. If 12 GB VRAM is available, Q4_K_M (1.71 GB, 4.9 GB memory) offers better quality. For 16 GB VRAM, Q5_K_M (1.99 GB, 5.2 GB memory) or Q8_0 (2.97 GB, 6.2 GB memory) can be used.

What GPU do you need for Home 3B v3?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q5_K_M (2.0 GB file, about 5.2 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 6.2 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (5.6 GB file, about 8.8 GB in use).

Which Home 3B v3 quant should you choose?

Q4_K_M is the usual starting point for Home 3B v3: it balances file size and quality well. Here it is a 1.7 GB file.

The Q8_0 file is 3.0 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 1.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturestablelm
Parameters2.8B
Layers32
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byacon96
FamilyHome
Licenseother
Downloads (HF)1,076
Last updated2025-10-25

Frequently asked questions about Home 3B v3

How much VRAM does Home 3B v3 need?

About 4.9 GB at Q4_K_M with an 8K context window. That is the 1.7 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 3B v3 on an 8 GB GPU?

Yes, with Q8_0: the 3.0 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Home 3B v3 GGUF?

It depends on the quant: Q2_K is 1.1 GB, Q2_K is 1.1 GB, Q3_K_M is 1.4 GB, Q3_K_M is 1.4 GB, Q4_K_M is 1.7 GB, Q4_K_M is 1.7 GB and 6 more.

What context length does Home 3B v3 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download Home 3B v3 GGUF?

The files are on Hugging Face in the acon96/Home-3B-v3-GGUF 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 3B v3 use?

Hugging Face lists the license as other. 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 3B v3 on 8 GB VRAM?

Yes, the Q2_K quantization uses 1.08 GB file size and requires approximately 4.3 GB memory at 8k context, fitting within 8 GB VRAM.

Does the model support multiple languages?

The tokenizer can handle German, Spanish, and French, but the base model lacks full multi‑language support.

What is the context length limit?

The model was trained with 4096 context tokens and does not support longer contexts.

Similar models

Browse all →

More from acon96

All by acon96 →

More Home models

All Home →

Other tiny models

All tiny models →