Jan nano F32 needs about 9.8 GB of memory at F16 (a 8.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 8.1 GB (BF16) to 16.1 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Jan nano F32 is a 4.02B-parameter Jan model in GGUF format, quantized by prithivMLmods. Its trained context length is 40K tokens. The repository has 3 quant files, from 8.1 GB (BF16) to 16.1 GB (F32).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 8.1 GB | 9.8 GB | Too big | Get file → | |
| F16 | 8.1 GB | 9.8 GB | Too big | Get file → | |
| F32 | 16.1 GB | 17.8 GB | Too big | Get file → |
What GPU do you need for Jan nano F32?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is BF16 (8.1 GB file, about 9.8 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (8.1 GB file, about 9.8 GB in use).
- 24 GB VRAM: the best quant that fits is F32 (16.1 GB file, about 17.8 GB in use).
Which Jan nano F32 quant should you choose?
F16 (8.1 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.
If memory is tight, the smallest file is BF16 at 8.1 GB, with the quality trade-offs that come with fewer bits. 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 Jan nano F32
How much VRAM does Jan nano F32 need?
About 9.8 GB at F16 with an 8K context window. That is the 8.1 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 F32 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Jan nano F32 GGUF?
It depends on the quant: BF16 is 8.1 GB, F16 is 8.1 GB, F32 is 16.1 GB.
What context length does Jan nano F32 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 F32 GGUF?
The files are on Hugging Face in the prithivMLmods/Jan-nano-F32-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 F32 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.