tiny agent needs about 1.9 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.3 GB to 2.5 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Tiny Agent: a lightweight Qwen3‑based LLM for local Windows office assistance
Tiny Agent is a 0.752 B parameter Qwen3 model fine‑tuned for reasoning and tool use. It runs locally via llama.cpp and supports 32,768 context tokens. The model is licensed under apache‑2.0.
Good at
- Reasoning
- Tool integration
- Office document editing
Limits
- No vision support
- Requires 8 k context for memory estimates
- No GPU needed but CPU intensive
Best for
- Local AI assistant in Word
- Excel formula generation
- PowerPoint slide editing
Who it’s for. Users who need an offline AI assistant for office tasks on Windows. The model runs on CPU without GPU or cloud API, making it suitable for privacy‑conscious environments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.3 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_M | 0.5 GB | 1.9 GB | Fits | Get file → | |
| Q4_K_M | 1.3 GB | 2.7 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 3.9 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K_M quant with file size 0.48 GB (est. memory 1.9 GB). If 16 GB VRAM is available, the 1.28 GB Q4_K_M file (est. memory 2.7 GB) offers a larger model. The 2.5 GB Q4_K_M file (est. memory 3.9 GB) requires more memory but provides the highest capacity.
What GPU do you need for tiny agent?
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 Q4_K_M (2.5 GB file, about 3.9 GB in use).
Which tiny agent quant should you choose?
Q4_K_M is the usual starting point for tiny agent: it balances file size and quality well. Here it is a 0.5 GB file.
If memory is tight, the smallest file is the first one in the table at 0.3 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 tiny agent
How much VRAM does tiny agent need?
About 1.9 GB at Q4_K_M with an 8K context window. That is the 0.5 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 tiny agent on an 8 GB GPU?
Yes, with Q4_K_M: the 2.5 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of tiny agent GGUF?
It depends on the quant: file is 0.3 GB, Q4_K_M is 0.5 GB, Q4_K_M is 1.3 GB, Q4_K_M is 2.5 GB.
What context length does tiny agent support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download tiny agent GGUF?
The files are on Hugging Face in the hkblockchaintechnology/tiny-agent-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does tiny agent 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 Tiny Agent on 8 GB VRAM?
Yes, the 0.48 GB Q4_K_M quant uses about 1.9 GB memory at 8 k context, fitting within 8 GB VRAM.
Does Tiny Agent support image input?
No, the model has no vision capability.
Is Tiny Agent free to use?
It is released under the apache‑2.0 license, allowing free use and modification.