AL

Alia40B

AliaGGUF by AbogaticUpdated 2025-01-21
Download on Hugging Face
Parameters40.4B
Context4K
Layers48
Architecturellama
Smallest quant23.3 GB
Quick answer

Alia40B needs about 25.4 GB of memory at Q4_0 (a 23.3 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 23.3 GB (Q4_0) to 43.0 GB (Q8_0).

Alia40B is a 40.4B-parameter Alia model in GGUF format, quantized by Abogatic. Its trained context length is 4K tokens. The repository has 2 quant files, from 23.3 GB (Q4_0) to 43.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_023.3 GB 24.6 GB
Too big Get file →
Q8_043.0 GB 44.3 GB
Too big Get file →

What GPU do you need for Alia40B?

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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q4_0 (23.3 GB file, about 25.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (43.0 GB file, about 45.1 GB in use).

Which Alia40B quant should you choose?

Q4_0 (23.3 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

Architecturellama
Parameters40.4B
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized byAbogatic
FamilyAlia
Base modelBSC-LT/ALIA-40b
Licenseapache-2.0
Downloads (HF)14
Last updated2025-01-21

Frequently asked questions about Alia40B

How much VRAM does Alia40B need?

About 25.4 GB at Q4_0 with an 8K context window. That is the 23.3 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 Alia40B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 25.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Alia40B GGUF?

It depends on the quant: Q4_0 is 23.3 GB, Q8_0 is 43.0 GB.

What context length does Alia40B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download Alia40B GGUF?

The files are on Hugging Face in the Abogatic/BSC-LT-ALIA-40b-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 Alia40B 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.

Other GGUFs of ALIA-40b

Similar models

Browse all →

More from Abogatic

All by Abogatic →

More Alia models

All Alia →

Other large models

All large models →