JerseyDevil 14b iMatrix needs about 11.2 GB of memory at its main file (a 8.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 8 quants, from 3.8 GB to 28.4 GB.
JerseyDevil 14b iMatrix is a 14.2B-parameter Jerseydevil model in GGUF format, quantized by MarsupialAI. Its trained context length is 8K tokens. The repository has 8 quant files, from 3.8 GB to 28.4 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 3.8 GB | 6.5 GB | Fits | Get file → | |
| — | 5.5 GB | 8.2 GB | Too big | Get file → | |
| — | 7.6 GB | 10.3 GB | Too big | Get file → | |
| — | 8.6 GB | 11.2 GB | Too big | Get file → | |
| — | 10.1 GB | 12.7 GB | Too big | Get file → | |
| — | 11.7 GB | 14.3 GB | Too big | Get file → | |
| — | 15.1 GB | 17.8 GB | Too big | Get file → | |
| — | 28.4 GB | 31.1 GB | Too big | Get file → |
What GPU do you need for JerseyDevil 14b iMatrix?
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: the best quant that fits is the main file (3.8 GB file, about 6.5 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (8.6 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (11.7 GB file, about 14.3 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (15.1 GB file, about 17.8 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (28.4 GB file, about 31.1 GB in use).
Which JerseyDevil 14b iMatrix quant should you choose?
If memory is tight, the smallest file is the first one in the table at 3.8 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 JerseyDevil 14b iMatrix
How much VRAM does JerseyDevil 14b iMatrix need?
About 11.2 GB at its main file with an 8K context window. That is the 8.6 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 JerseyDevil 14b iMatrix on an 8 GB GPU?
Yes, with the smaller files: the 3.8 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of JerseyDevil 14b iMatrix GGUF?
It depends on the quant: file is 3.8 GB, file is 5.5 GB, file is 7.6 GB, file is 8.6 GB, file is 10.1 GB, file is 11.7 GB and 2 more.
What context length does JerseyDevil 14b iMatrix support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.1 GB at 8K and 2.1 GB at 8K.
Where can I download JerseyDevil 14b iMatrix GGUF?
The files are on Hugging Face in the MarsupialAI/JerseyDevil-14b_iMatrix_GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.