Jan nano needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 14 quants, from 1.9 GB (Q3_K_S) to 4.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Compact 4B Qwen3 model with 40960 token context
Jan Nano is a 4‑billion parameter language model based on Qwen3. It offers a 40960 token context window and is optimized for local deployment. The model is non‑thinking and supports tool use and research tasks.
Good at
- Tool integration
- Long‑context handling
- Compact size
Limits
- No vision support
- Requires 8k context for memory estimates
- Apache‑2.0 license
Best for
- Local research assistants
- Embedded text generation
- Tool‑augmented workflows
Who it’s for. Developers and researchers who need a small, efficient model for local or embedded use. It is suitable for applications that require extended context and tool integration without large GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 1.9 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_M | 2.1 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_L | 2.2 GB | 3.9 GB | Fits | Get file → | |
| IQ4_XS | 2.3 GB | 4.0 GB | Fits | Get file → | |
| Q4_0 | 2.4 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_S | 2.4 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q4_1 | 2.6 GB | 4.3 GB | Fits | Get file → | |
| Q5_0 | 2.8 GB | 4.5 GB | Fits | Get file → | |
| Q5_K_S | 2.8 GB | 4.5 GB | Fits | Get file → | |
| Q5_K_M | 2.9 GB | 4.6 GB | Fits | Get file → | |
| Q5_1 | 3.1 GB | 4.8 GB | Fits | Get file → | |
| Q6_K | 3.3 GB | 5.0 GB | Fits | Get file → | |
| Q8_0 | 4.3 GB | 6.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 (est. 4.1 GB) or Q4_K_S (est. 4.1 GB). If 6 GB is available, Q5_0 (est. 4.5 GB) or Q5_K_S (est. 4.5 GB) are suitable. For 4 GB VRAM, Q3_K_S (est. 3.6 GB) or Q3_K_M (est. 3.8 GB) are recommended.
What GPU do you need for Jan nano?
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 IQ4_XS (2.3 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
Which Jan nano quant should you choose?
Q4_K_M is the usual starting point for Jan nano: it balances file size and quality well. Here it is a 2.5 GB file.
The Q8_0 file is 4.3 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q3_K_S at 1.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Jan nano
How much VRAM does Jan nano need?
About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 Jan nano on an 8 GB GPU?
Yes, with Q8_0: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Jan nano GGUF?
It depends on the quant: Q3_K_S is 1.9 GB, Q3_K_M is 2.1 GB, Q3_K_L is 2.2 GB, IQ4_XS is 2.3 GB, Q4_0 is 2.4 GB, Q4_K_S is 2.4 GB and 8 more.
What context length does Jan nano support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download Jan nano GGUF?
The files are on Hugging Face in the Menlo/Jan-nano-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 Jan nano 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 Jan Nano on 8 GB VRAM?
Yes, Q4_0 or Q4_K_S quantizations fit within 8 GB VRAM with an estimated 4.1 GB usage.
Does Jan Nano support vision tasks?
No, Jan Nano is a text‑only model with no vision capability.