LI

Liquid-FNC-0.5

LiquidGGUF by Liquid1Updated 2024-07-10
Download on Hugging Face
Parameters494M
Context32K
Layers24
Architectureqwen2
Smallest quant0.4 GB
Quick answer

Liquid-FNC-0.5 needs about 1.0 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.4 GB (Q4_K_M) to 1.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.

Liquid-FNC-0.5 is a 494M-parameter Liquid model in GGUF format, quantized by Liquid1. Its trained context length is 32K tokens. The repository has 2 quant files, from 0.4 GB (Q4_K_M) to 1.0 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.4 GB 1.0 GB
Fits Get file →
F161.0 GB 1.6 GB
Fits Get file →

What GPU do you need for Liquid-FNC-0.5?

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: the best quant that fits is F16 (1.0 GB file, about 1.6 GB in use).

Which Liquid-FNC-0.5 quant should you choose?

Q4_K_M is the usual starting point for Liquid-FNC-0.5: it balances file size and quality well. Here it is a 0.4 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters494M
Layers24
Trained context32,768 tokens
KV cache (fp16)12 KB per token

Source

Quantized byLiquid1
FamilyLiquid
Licenseapache-2.0
Downloads (HF)49
Last updated2024-07-10

Frequently asked questions about Liquid-FNC-0.5

How much VRAM does Liquid-FNC-0.5 need?

About 1.0 GB at Q4_K_M with an 8K context window. That is the 0.4 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 Liquid-FNC-0.5 on an 8 GB GPU?

Yes, with F16: the 1.0 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Liquid-FNC-0.5 GGUF?

It depends on the quant: Q4_K_M is 0.4 GB, F16 is 1.0 GB.

What context length does Liquid-FNC-0.5 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.

Where can I download Liquid-FNC-0.5 GGUF?

The files are on Hugging Face in the Liquid1/Liquid-FNC-0.5 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Liquid-FNC-0.5 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.

Similar models

Browse all →

More from Liquid1

All by Liquid1 →

More Liquid models

All Liquid →

Other tiny models

All tiny models →