MA

jb

ManancodeGGUF by manancodeUpdated 2025-09-27
Download on Hugging Face
Parameters2.94B
Context512
Layers32
Architecturet5
Smallest quant1.7 GB
Quick answer

jb needs about 4.3 GB of memory at its main file (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU.

jb is a 2.94B-parameter Manancode model in GGUF format, quantized by manancode. Its trained context length is 512 tokens. The repository has 1 quant file, from 1.7 GB to 1.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.7 GB 2.3 GB
Fits Get file →

What GPU do you need for jb?

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: the best quant that fits is the main file (1.7 GB file, about 4.3 GB in use).

Specifications

Architecture from the GGUF header

Architecturet5
Parameters2.94B
Layers32
Trained context512 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymanancode
FamilyManancode
Repositorymanancode/jb
Downloads (HF)13
Last updated2025-09-27

Frequently asked questions about jb

How much VRAM does jb need?

About 4.3 GB at its main file with an 8K context window. That is the 1.7 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 jb on an 8 GB GPU?

Yes, with the smaller files: the 1.7 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of jb GGUF?

It depends on the quant: file is 1.7 GB.

What context length does jb support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 2.1 GB at 8K and 0.1 GB at 512.

Where can I download jb GGUF?

The files are on Hugging Face in the manancode/jb repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does jb use?

Hugging Face lists the license as cc-by-nc-sa-3.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from manancode

All by manancode →

More Manancode models

All Manancode →

Other tiny models

All tiny models →