LI

lightblue qarasu 14B chat plus unleashed

LightblueGGUF by mmngaUpdated 2024-05-07
Download on Hugging Face
Parameters14.2B
Context8K
Layers40
Architectureqwen
Smallest quant6.6 GB
Quick answer

lightblue qarasu 14B chat plus unleashed needs about 16.7 GB of memory at Q4_K_M (a 9.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 6.6 GB (Q2_K) to 15.1 GB (Q8_0).

lightblue qarasu 14B chat plus unleashed is a 14.2B-parameter Lightblue model in GGUF format, quantized by mmnga. Its trained context length is 8K tokens. The repository has 12 quant files, from 6.6 GB (Q2_K) to 15.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K6.6 GB 13.8 GB
Too big Get file →
Q3_K_S6.9 GB 14.2 GB
Too big Get file →
Q3_K_M7.7 GB 14.9 GB
Too big Get file →
Q3_K_L8.0 GB 15.2 GB
Too big Get file →
Q4_08.2 GB 15.4 GB
Too big Get file →
Q4_K_S8.5 GB 15.8 GB
Too big Get file →
Q4_K_M9.4 GB 16.7 GB
Too big Get file →
Q5_09.9 GB 17.1 GB
Too big Get file →
Q5_K_S10.0 GB 17.2 GB
Too big Get file →
Q5_K_M10.9 GB 18.1 GB
Too big Get file →
Q6_K12.3 GB 19.5 GB
Too big Get file →
Q8_015.1 GB 22.3 GB
Too big Get file →

What GPU do you need for lightblue qarasu 14B chat plus unleashed?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q4_K_S (8.5 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.1 GB file, about 22.3 GB in use).

Which lightblue qarasu 14B chat plus unleashed quant should you choose?

Q4_K_M is the usual starting point for lightblue qarasu 14B chat plus unleashed: it balances file size and quality well. Here it is a 9.4 GB file.

The Q8_0 file is 15.1 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 6.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen
Parameters14.2B
Layers40
Trained context8,192 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymmnga
FamilyLightblue
Licenseother
Downloads (HF)384
Last updated2024-05-07

Frequently asked questions about lightblue qarasu 14B chat plus unleashed

How much VRAM does lightblue qarasu 14B chat plus unleashed need?

About 16.7 GB at Q4_K_M with an 8K context window. That is the 9.4 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 lightblue qarasu 14B chat plus unleashed on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of lightblue qarasu 14B chat plus unleashed GGUF?

It depends on the quant: Q2_K is 6.6 GB, Q3_K_S is 6.9 GB, Q3_K_M is 7.7 GB, Q3_K_L is 8.0 GB, Q4_0 is 8.2 GB, Q4_K_S is 8.5 GB and 6 more.

What context length does lightblue qarasu 14B chat plus unleashed support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 6.7 GB at 8K and 6.7 GB at 8K.

Where can I download lightblue qarasu 14B chat plus unleashed GGUF?

The files are on Hugging Face in the mmnga/lightblue-qarasu-14B-chat-plus-unleashed-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 lightblue qarasu 14B chat plus unleashed use?

Hugging Face lists the license as other. 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 mmnga

All by mmnga →

More Lightblue models

All Lightblue →

Other medium models

All medium models →