gemma 3 4b est v1 needs about 4.1 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.5 GB (Q4_K_M) to 7.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
Gemma 3 4B Estonian (v1) – a small, mobile‑friendly Estonian LLM
Gemma 3 4B Estonian (v1) is a 3.88 billion‑parameter model fine‑tuned for Estonian. It was trained on 161.5 M Estonian web tokens and 30.5 k instruction pairs. The model runs comfortably on phones and low‑end GPUs.
Good at
- Estonian language tasks
- Summarization
- Inflection
Limits
- Trained primarily for Estonian; English performance not evaluated
- No vision support
- Context up to 4096 tokens recommended
Best for
- Estonian chat applications
- Estonian summarization
- Estonian QA
Who it’s for. Developers and researchers needing a lightweight Estonian LLM that can run on mobile devices or consumer GPUs. The model is suitable for local deployment via llama.cpp, Ollama, LM Studio, PocketPal AI, or ChatterUI.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q5_K_M | 2.8 GB | 4.5 GB | Fits | Get file → | |
| F16 | 7.8 GB | 9.4 GB | Too big | Get file → |
For 8 GB VRAM use the Q4_K_M quant (file size 2.49 GB, estimated 4.1 GB memory at 8 k context). For 12 GB VRAM the Q5_K_M quant (2.83 GB, 4.5 GB memory) is suitable. If larger memory is available, the F16 quant (7.77 GB, 9.4 GB memory) provides the highest precision.
What GPU do you need for gemma 3 4b est v1?
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 (2.8 GB file, about 4.5 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (2.8 GB file, about 4.5 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (7.8 GB file, about 9.4 GB in use).
Which gemma 3 4b est v1 quant should you choose?
Q4_K_M is the usual starting point for gemma 3 4b est v1: it balances file size and quality well. Here it is a 2.5 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about gemma 3 4b est v1
How much VRAM does gemma 3 4b est v1 need?
About 4.1 GB at Q4_K_M with an 8K context window. That is the 2.5 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 3 4b est v1 on an 8 GB GPU?
Yes, with Q5_K_M: the 2.8 GB file needs about 4.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of gemma 3 4b est v1 GGUF?
It depends on the quant: Q4_K_M is 2.5 GB, Q5_K_M is 2.8 GB, F16 is 7.8 GB.
What context length does gemma 3 4b est v1 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.
Where can I download gemma 3 4b est v1 GGUF?
The files are on Hugging Face in the Abdusin/gemma-3-4b-est-v1 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 3 4b est v1 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_K_M quant requires about 4.1 GB memory at 8 k context and fits in 8 GB VRAM.
Does it support English?
English was not evaluated after training; performance may be degraded.
What is the recommended context length?
Context up to 4096 tokens is recommended for stable performance.