AS

astramix l2 7b

AstramixGGUF by androlikeUpdated 2023-08-31
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant4.8 GB
Quick answer

astramix l2 7b needs about 9.6 GB of memory at Q5_K_M (a 4.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 4.8 GB (Q5_K_M) to 13.5 GB (F16).

astramix l2 7b is a 6.74B-parameter Astramix model in GGUF format, quantized by androlike. Its trained context length is 4K tokens. The repository has 2 quant files, from 4.8 GB (Q5_K_M) to 13.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M4.8 GB 7.4 GB
Tight Get file →
F1613.5 GB 16.1 GB
Too big Get file →

What GPU do you need for astramix l2 7b?

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: the best quant that fits is Q5_K_M (4.8 GB file, about 9.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (4.8 GB file, about 9.6 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (13.5 GB file, about 18.3 GB in use).

Which astramix l2 7b quant should you choose?

Q5_K_M (4.8 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byandrolike
FamilyAstramix
Licenseother
Downloads (HF)38
Last updated2023-08-31

Frequently asked questions about astramix l2 7b

How much VRAM does astramix l2 7b need?

About 9.6 GB at Q5_K_M with an 8K context window. That is the 4.8 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 astramix l2 7b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of astramix l2 7b GGUF?

It depends on the quant: Q5_K_M is 4.8 GB, F16 is 13.5 GB.

What context length does astramix l2 7b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download astramix l2 7b GGUF?

The files are on Hugging Face in the androlike/astramix_l2_7b_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 astramix l2 7b 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 androlike

All by androlike →

Other small models

All small models →