cagliari 114m needs about 0.9 GB of memory at F16 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU.
Cagliari-114M: A lightweight Qwen3-compatible language model
Cagliari-114M is a 114M parameter model built on the Qwen3 architecture. It uses a GPT-2 BPE tokenizer with four special tokens and was trained from scratch on 8.16B tokens. The model provides completion-only output with a 1024 token context window.
Good at
- Fast inference on low‑memory GPUs
- Simple text generation
- Baseline Qwen3 compatibility
Limits
- No instruction or chat behavior
- Limited factual recall and reasoning
- Context length 1024 tokens
Best for
- Quick prototyping
- Embedded devices
- Educational demos
Who it’s for. Developers needing a small, fast Qwen3-compatible model for experimentation or low‑resource deployment. Suitable for projects that do not require instruction following or advanced reasoning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.3 GB | 0.8 GB | Fits | Get file → |
The only available quantization is F16, with a file size of 0.29 GB and an estimated memory usage of 0.9 GB at 8 k context. This is suitable for systems with at least 1 GB VRAM. No other quants are provided, so memory estimates are approximate.
What GPU do you need for cagliari 114m?
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 (0.3 GB file, about 0.9 GB in use).
Which cagliari 114m quant should you choose?
F16 (0.3 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about cagliari 114m
How much VRAM does cagliari 114m need?
About 0.9 GB at F16 with an 8K context window. That is the 0.3 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 cagliari 114m on an 8 GB GPU?
Yes, with F16: the 0.3 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of cagliari 114m GGUF?
It depends on the quant: F16 is 0.3 GB.
What context length does cagliari 114m support?
The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 1K.
Where can I download cagliari 114m GGUF?
The files are on Hugging Face in the Meridian-MRM/cagliari-114m repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does cagliari 114m 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 Cagliari-114M on 1 GB VRAM?
Yes, the F16 quant uses about 0.9 GB at 8 k context, fitting within 1 GB VRAM.
Does the model support chat or instruction following?
No, it is a completion-only model with no instruction tuning or chat behavior.
What license applies to this model?
The model is released under the Apache 2.0 license.