HA

Hathor Trihexa L3 8B Anarchy Edition

HathorGGUF by Reiterate3680Updated 2024-12-04
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant5.3 GB
Quick answer

Hathor Trihexa L3 8B Anarchy Edition needs about 6.9 GB of memory at Q4_K_L (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 5.3 GB (Q4_K_L) to 6.9 GB (Q6_K_L).

Hathor Trihexa L3 8B Anarchy Edition is a 8.03B-parameter Hathor model in GGUF format, quantized by Reiterate3680. Its trained context length is 8K tokens. The repository has 2 quant files, from 5.3 GB (Q4_K_L) to 6.9 GB (Q6_K_L).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_L5.3 GB 6.9 GB
Fits Get file →
Q6_K_L6.9 GB 8.4 GB
Too big Get file →

What GPU do you need for Hathor Trihexa L3 8B Anarchy Edition?

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: the best quant that fits is Q4_K_L (5.3 GB file, about 6.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K_L (6.9 GB file, about 8.4 GB in use).

Which Hathor Trihexa L3 8B Anarchy Edition quant should you choose?

Q4_K_L (5.3 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
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byReiterate3680
FamilyHathor
Licenseother
Downloads (HF)31
Last updated2024-12-04

Frequently asked questions about Hathor Trihexa L3 8B Anarchy Edition

How much VRAM does Hathor Trihexa L3 8B Anarchy Edition need?

About 6.9 GB at Q4_K_L with an 8K context window. That is the 5.3 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 Hathor Trihexa L3 8B Anarchy Edition on an 8 GB GPU?

Yes, with Q4_K_L: the 5.3 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Hathor Trihexa L3 8B Anarchy Edition GGUF?

It depends on the quant: Q4_K_L is 5.3 GB, Q6_K_L is 6.9 GB.

What context length does Hathor Trihexa L3 8B Anarchy Edition support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download Hathor Trihexa L3 8B Anarchy Edition GGUF?

The files are on Hugging Face in the Reiterate3680/Hathor_Trihexa-L3-8B-Anarchy_Edition-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 Hathor Trihexa L3 8B Anarchy Edition 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.

Other GGUFs of Hathor_Trihexa-L3-8B-Anarchy_Edition

Similar models

Browse all →

More from Reiterate3680

All by Reiterate3680 →

More Hathor models

All Hathor →

Other small models

All small models →