J1 needs about 17.2 GB of memory at its main file (a 14.9 GB file) with an 8K context window, so it fits on a 24 GB GPU.
J1 is a 20.4B-parameter model in GGUF format, quantized by z1i1. The repository has 1 quant file, from 14.9 GB to 14.9 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 14.9 GB | 17.2 GB | Too big | Get file → |
What GPU do you need for J1?
These figures add the file size, an fp16 KV cache at an 8K context window 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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is the main file (14.9 GB file, about 17.2 GB in use).
Specifications
Architecture from the GGUF header
Frequently asked questions about J1
How much VRAM does J1 need?
About 17.2 GB at its main file with an 8K context window. That is the 14.9 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 J1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of J1 GGUF?
It depends on the quant: file is 14.9 GB.
Where can I download J1 GGUF?
The files are on Hugging Face in the z1i1/J1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.