BI

BitDance 14B 64x merge

BitdanceGGUF by smthemUpdated 2026-02-26
Download on Hugging Face
Parameters14.8B
Context—
Layers—
Architectureqwen
Smallest quant17.2 GB
Quick answer

BitDance 14B 64x merge needs about 19.7 GB of memory at Q4_K_S (a 17.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 17.2 GB (Q4_K_S) to 21.5 GB (Q8_0).

BitDance 14B 64x merge is a 14.8B-parameter Bitdance model in GGUF format, quantized by smthem. The repository has 2 quant files, from 17.2 GB (Q4_K_S) to 21.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S17.2 GB 19.7 GB
Too big Get file →
Q8_021.5 GB 24.6 GB
Too big Get file →

What GPU do you need for BitDance 14B 64x merge?

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 Q4_K_S (17.2 GB file, about 19.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (21.5 GB file, about 24.6 GB in use).

Which BitDance 14B 64x merge quant should you choose?

Q4_K_S (17.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen
Parameters14.8B

Source

Quantized bysmthem
FamilyBitdance
Licensemit
Downloads (HF)28
Last updated2026-02-26

Frequently asked questions about BitDance 14B 64x merge

How much VRAM does BitDance 14B 64x merge need?

About 19.7 GB at Q4_K_S with an 8K context window. That is the 17.2 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 BitDance 14B 64x merge on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of BitDance 14B 64x merge GGUF?

It depends on the quant: Q4_K_S is 17.2 GB, Q8_0 is 21.5 GB.

Where can I download BitDance 14B 64x merge GGUF?

The files are on Hugging Face in the smthem/BitDance-14B-64x-merge-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 BitDance 14B 64x merge use?

Hugging Face lists the license as mit. 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 smthem

All by smthem →

Other medium models

All medium models →