CA

CausalLM 14B

CausallmGGUF by LimourUpdated 2024-03-30
Download on Hugging Face
Parameters14.2B
Context8K
Layers40
Architecturellama
Smallest quant5.0 GB
Quick answer

CausalLM 14B needs about 13.7 GB of memory at IQ3_XS (a 6.5 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 5.0 GB (IQ2_XXS) to 7.8 GB (IQ4_XS).

CausalLM 14B is a 14.2B-parameter Causallm model in GGUF format, quantized by Limour. Its trained context length is 8K tokens. The repository has 3 quant files, from 5.0 GB (IQ2_XXS) to 7.8 GB (IQ4_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS5.0 GB 12.2 GB
Too big Get file →
IQ3_XS6.5 GB 13.7 GB
Too big Get file →
IQ4_XS7.8 GB 15.1 GB
Too big Get file →

What GPU do you need for CausalLM 14B?

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 IQ4_XS (7.8 GB file, about 15.1 GB in use).

Which CausalLM 14B quant should you choose?

IQ3_XS (6.5 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ2_XXS at 5.0 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

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

Source

Quantized byLimour
FamilyCausallm
Licensewtfpl
Downloads (HF)112
Last updated2024-03-30

Frequently asked questions about CausalLM 14B

How much VRAM does CausalLM 14B need?

About 13.7 GB at IQ3_XS with an 8K context window. That is the 6.5 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 CausalLM 14B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of CausalLM 14B GGUF?

It depends on the quant: IQ2_XXS is 5.0 GB, IQ3_XS is 6.5 GB, IQ4_XS is 7.8 GB.

What context length does CausalLM 14B 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 CausalLM 14B GGUF?

The files are on Hugging Face in the Limour/CausalLM-14B-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 CausalLM 14B use?

Hugging Face lists the license as wtfpl. 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 Limour

All by Limour →

More Causallm models

All Causallm →

Other medium models

All medium models →