Gemma 4 E2B Home Assistant needs about 4.5 GB of memory at Q4_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 3.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.
Gemma 4 E2B Home Assistant – fine‑tuned for smart‑home tool calls
Gemma 4 E2B Home Assistant is a 4.63 billion‑parameter model fine‑tuned to control smart‑home devices via natural language. It emits tool calls that can be executed by a home‑assistant system. The model is a drop‑in replacement for the base Gemma4 checkpoint.
Good at
- Natural language control of smart‑home devices
- Tool‑call generation
- Reasoning with context up to 131072 tokens
Limits
- No vision or audio support in the fine‑tuned weights
- Requires a system prompt with device and tool schemas
- License governed by Gemma Terms of Use
Best for
- Home‑assistant command generation
- Automated smart‑home workflows
- Tool‑call debugging
Who it’s for. Developers building voice‑oriented home‑assistant applications who need a lightweight, text‑only model that can emit structured tool calls. The model is suitable for local deployment via llama.cpp or Ollama.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.1 GB | Fits | Get file → | |
| IQ1_S | 2.3 GB | 3.4 GB | Fits | Get file → | |
| IQ1_M | 2.4 GB | 3.4 GB | Fits | Get file → | |
| IQ2_XXS | 2.4 GB | 3.5 GB | Fits | Get file → | |
| IQ2_XS | 2.5 GB | 3.6 GB | Fits | Get file → | |
| IQ2_S | 2.5 GB | 3.6 GB | Fits | Get file → | |
| IQ2_M | 2.6 GB | 3.6 GB | Fits | Get file → | |
| IQ3_XXS | 2.6 GB | 3.7 GB | Fits | Get file → | |
| Q2_K_S | 2.9 GB | 4.0 GB | Fits | Get file → | |
| Q2_K | 3.0 GB | 4.1 GB | Fits | Get file → | |
| IQ3_XS | 3.1 GB | 4.1 GB | Fits | Get file → | |
| Q3_K_S | 3.1 GB | 4.2 GB | Fits | Get file → | |
| IQ3_S | 3.1 GB | 4.2 GB | Fits | Get file → | |
| IQ3_M | 3.1 GB | 4.2 GB | Fits | Get file → | |
| Q3_K_M | 3.2 GB | 4.3 GB | Fits | Get file → | |
| Q3_K_L | 3.3 GB | 4.4 GB | Fits | Get file → | |
| IQ4_XS | 3.3 GB | 4.4 GB | Fits | Get file → | |
| IQ4_NL | 3.4 GB | 4.4 GB | Fits | Get file → | |
| Q4_0 | 3.4 GB | 4.4 GB | Fits | Get file → | |
| Q4_K_S | 3.4 GB | 4.4 GB | Fits | Get file → | |
| Q4_K_M | 3.4 GB | 4.5 GB | Fits | Get file → | |
| Q4_1 | 3.5 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_S | 3.6 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_M | 3.6 GB | 4.7 GB | Fits | Get file → | |
| Q6_K | 3.8 GB | 4.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 (file size 3.35 GB, estimated 4.4 GB memory). For 6 GB VRAM, Q2_K (2.98 GB, 4.1 GB memory) or IQ2_XS (2.48 GB, 3.6 GB memory). For 4 GB VRAM, IQ1_S (2.32 GB, 3.4 GB memory) or IQ1_M (2.36 GB, 3.4 GB memory).
What GPU do you need for Gemma 4 E2B Home Assistant?
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 Q2_K_S (2.9 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.8 GB file, about 4.9 GB in use).
Which Gemma 4 E2B Home Assistant quant should you choose?
Q4_K_M is the usual starting point for Gemma 4 E2B Home Assistant: it balances file size and quality well. Here it is a 3.4 GB file.
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
Source
Frequently asked questions about Gemma 4 E2B Home Assistant
How much VRAM does Gemma 4 E2B Home Assistant need?
About 4.5 GB at Q4_K_M with an 8K context window. That is the 3.4 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 Gemma 4 E2B Home Assistant on an 8 GB GPU?
Yes, with Q6_K: the 3.8 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gemma 4 E2B Home Assistant GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 2.3 GB, IQ1_M is 2.4 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.5 GB and 19 more.
What context length does Gemma 4 E2B Home Assistant support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.
Where can I download Gemma 4 E2B Home Assistant GGUF?
The files are on Hugging Face in the mradermacher/gemma-4-E2B-home-assistant-i1-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 Gemma 4 E2B Home Assistant 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 this model on 8 GB VRAM?
Yes, the Q4_0 quant (3.35 GB file) uses about 4.4 GB memory at 8 k context, which fits 8 GB VRAM.
Does the model support vision or audio input?
No, the fine‑tuned weights only include the text projection; vision and audio towers are unchanged but not used.
What license applies to this model?
The Gemma license applies; you must accept the Gemma Terms of Use to use the weights.