Kolada writer needs about 1.3 GB of memory at its main file (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.2 GB to 0.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
Kolada Writer – a lightweight text‑editing LLM for on‑device use
Kolada Writer is a 1.17B parameter model derived from LiquidAI/LFM2.5‑1.2B‑Instruct. It corrects typos, spelling and grammar and generates one‑line summaries. The model runs locally and never sends data to external servers.
Good at
- Grammar correction
- Spelling fixes
- One‑line summarisation
Limits
- No vision support
- Not suited for knowledge‑intensive tasks
- Not a mixture of experts
Best for
- Note‑taking apps
- Personal writing assistants
- Offline text editing
Who it’s for. Developers building local writing assistants or note‑taking applications that require on‑device text correction and summarisation. The model is ideal for users who need privacy and low‑resource inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 1.3 GB | Fits | Get file → | |
| — | 0.7 GB | 1.8 GB | Fits | Get file → |
For 8 GB VRAM, the 0.23 GB GGUF file uses about 1.3 GB of memory at 8k context, while the 0.73 GB file uses about 1.8 GB. Either file fits comfortably on 8 GB VRAM. Choose the smaller file for tighter memory budgets.
What GPU do you need for Kolada writer?
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 the main file (0.7 GB file, about 1.8 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Kolada writer
How much VRAM does Kolada writer need?
About 1.3 GB at its main file with an 8K context window. That is the 0.2 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 Kolada writer on an 8 GB GPU?
Yes, with the smaller files: the 0.7 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Kolada writer GGUF?
It depends on the quant: file is 0.2 GB, file is 0.7 GB.
What context length does Kolada writer support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.
Where can I download Kolada writer GGUF?
The files are on Hugging Face in the kolada-app/Kolada-writer repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Kolada writer use?
Hugging Face lists the license as cc-by-nc-4.0. 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 Kolada Writer on 8 GB VRAM?
Yes. The 0.23 GB or 0.73 GB GGUF files use approximately 1.3 GB or 1.8 GB of VRAM at 8k context, well below 8 GB.
Does Kolada Writer support image input?
No. The model is text‑only and does not process visual data.
What license applies to Kolada Writer?
The model is released under cc‑by‑nc‑4.0, allowing non‑commercial use with attribution.