cowork companion needs about 1.3 GB of memory at its main file (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.2 GB to 0.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
Cowork Companion – a 350M parameter LFM2 hybrid model for tool‑enabled text tasks
Cowork Companion is a 350M parameter LFM2 model derived from LFM2.5‑350M‑Base. It supports tool usage and is designed for on‑device deployment. The model has a 128000 token context window and is trained on 28T tokens.
Good at
- Tool‑enabled text generation
- On‑device inference
- Fine‑tuning for domain tasks
Limits
- No vision support
- Requires fine‑tuning for best results
- License type is other
Best for
- Developing lightweight assistants
- Fine‑tuning for specific domains
- Deploying on edge devices
Who it’s for. Developers looking for a small, on‑device LFM2 model that can be fine‑tuned for specialized tasks. The model is suitable for those who need tool integration and a 128000 token context window.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 1.3 GB | Fits | Get file → | |
| — | 0.3 GB | 1.3 GB | Fits | Get file → | |
| — | 0.3 GB | 1.3 GB | Fits | Get file → | |
| — | 0.4 GB | 1.4 GB | Fits | Get file → |
The smallest quant file is 0.23 GB and uses about 1.3 GB of VRAM at 8 k context. For 8 GB VRAM, use the 0.23 GB or 0.26 GB files. For 12 GB VRAM, the 0.29 GB or 0.38 GB files are suitable. Memory estimates are approximate.
What GPU do you need for cowork companion?
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 (0.4 GB file, about 1.4 GB in use).
Which cowork companion quant should you choose?
If memory is tight, the smallest file is the first one in the table at 0.2 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 cowork companion
How much VRAM does cowork companion need?
About 1.3 GB at its main file 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 cowork companion on an 8 GB GPU?
Yes, with the smaller files: the 0.4 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of cowork companion GGUF?
It depends on the quant: file is 0.2 GB, file is 0.3 GB, file is 0.3 GB, file is 0.4 GB.
What context length does cowork companion 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 cowork companion GGUF?
The files are on Hugging Face in the chadstthomas/cowork-companion repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does cowork companion use?
Hugging Face lists the license as other. 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 Cowork Companion on 8 GB VRAM?
Yes, the 0.23 GB and 0.26 GB quant files use about 1.3 GB of VRAM at 8 k context, fitting within 8 GB.
Does Cowork Companion support vision tasks?
No, the model is text‑only and does not support vision.
What is the context length of this model?
The model supports 128000 tokens of context.