Udgam-384M-Base needs about 1.2 GB of memory at Q8_0 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.4 GB (Q8_0) to 0.8 GB (F16).
Udgam-384M-Base: 384M‑parameter Gemma4 decoder-only model
Udgam-384M-Base is a 384M‑parameter English base model trained from scratch. It is a decoder‑only transformer compatible with Gemma4 architecture and runs unmodified in transformers, llama.cpp, Ollama, LM Studio and MLX. The model is not instruction‑tuned or safety‑tuned and has no chat behaviour of its own.
Good at
- Reasoning
- Tool usage
- Text continuation
Limits
- No chat or instruction tuning
- No vision support
- Requires special token handling
Best for
- On‑device text generation
- Tool‑calling prototypes
- Baseline for fine‑tuning
Who it’s for. Developers and researchers who need a lightweight, open‑source Gemma4 base model for experimentation or on‑device deployment. It is suitable for building chat or tool‑calling variants such as Udgam-384M-Chat.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.4 GB | 1.0 GB | Fits | Get file → | |
| F16 | 0.8 GB | 1.4 GB | Fits | Get file → |
For 8 GB VRAM use the Q8_0 quantized file (0.41 GB, ~1.2 GB memory at 8 k context). For 4 GB VRAM use the F16 quantized file (0.77 GB, ~1.6 GB memory at 8 k context). These estimates are approximate.
What GPU do you need for Udgam-384M-Base?
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 F16 (0.8 GB file, about 1.6 GB in use).
Which Udgam-384M-Base quant should you choose?
Q8_0 (0.4 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Udgam-384M-Base
How much VRAM does Udgam-384M-Base need?
About 1.2 GB at Q8_0 with an 8K context window. That is the 0.4 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 Udgam-384M-Base on an 8 GB GPU?
Yes, with F16: the 0.8 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Udgam-384M-Base GGUF?
It depends on the quant: Q8_0 is 0.4 GB, F16 is 0.8 GB.
What context length does Udgam-384M-Base support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.1 GB at 2K.
Where can I download Udgam-384M-Base GGUF?
The files are on Hugging Face in the udgamlabs/Udgam-384M-Base repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Udgam-384M-Base 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 Udgam-384M-Base on 8 GB VRAM?
Yes, the Q8_0 quantized file is 0.41 GB and requires about 1.2 GB memory at 8 k context, which fits in 8 GB VRAM.
Does Udgam-384M-Base support chat?
No, it is a base model with no chat behaviour. Use Udgam-384M-Chat for chat functionality.