LL

marathi llama3

LlamaGGUF by Echelon-AIUpdated 2024-07-01
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant5.7 GB
Quick answer

marathi llama3 needs about 10.1 GB of memory at Q8_0 (a 8.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 5.7 GB (Q5_K_M) to 16.1 GB (BF16).

marathi llama3 is a 8.03B-parameter Llama model in GGUF format, quantized by Echelon-AI. Its trained context length is 8K tokens. The repository has 3 quant files, from 5.7 GB (Q5_K_M) to 16.1 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →
BF1616.1 GB 17.6 GB
Too big Get file →

What GPU do you need for marathi llama3?

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 Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (16.1 GB file, about 17.6 GB in use).

Which marathi llama3 quant should you choose?

Q8_0 (8.5 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q5_K_M at 5.7 GB, with the quality trade-offs that come with fewer bits. 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
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byEchelon-AI
FamilyLlama
Licensellama3
Downloads (HF)74
Last updated2024-07-01

Frequently asked questions about marathi llama3

How much VRAM does marathi llama3 need?

About 10.1 GB at Q8_0 with an 8K context window. That is the 8.5 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 marathi llama3 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of marathi llama3 GGUF?

It depends on the quant: Q5_K_M is 5.7 GB, Q8_0 is 8.5 GB, BF16 is 16.1 GB.

What context length does marathi llama3 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 marathi llama3 GGUF?

The files are on Hugging Face in the Echelon-AI/marathi-llama3-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 marathi llama3 use?

Hugging Face lists the license as llama3. 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 Echelon-AI

All by Echelon-AI →

More Llama models

All Llama →

Other small models

All small models →