LL

llama-3-70B-instruct-uncensored-lora

LlamaGGUF by perletsUpdated 2024-07-03
Download on Hugging Face
Parameters4M
Context8K
Layers80
Architecturellama
Smallest quant0.0 GB
Quick answer

llama-3-70B-instruct-uncensored-lora needs about 3.2 GB of memory at F16 (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.0 GB (F16) to 0.0 GB (F32).

llama-3-70B-instruct-uncensored-lora is a 4M-parameter Llama model in GGUF format, quantized by perlets. Its trained context length is 8K tokens. The repository has 4 quant files, from 0.0 GB (F16) to 0.0 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.0 GB 3.2 GB
Fits Get file →
F160.0 GB 3.2 GB
Fits Get file →
F320.0 GB 3.2 GB
Fits Get file →
F320.0 GB 3.2 GB
Fits Get file →

What GPU do you need for llama-3-70B-instruct-uncensored-lora?

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: the best quant that fits is F16 (0.0 GB file, about 3.2 GB in use).

Which llama-3-70B-instruct-uncensored-lora quant should you choose?

F16 (0.0 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is F16 at 0.0 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters4M
Layers80
Trained context8,192 tokens
KV cache (fp16)320 KB per token

Source

Quantized byperlets
FamilyLlama
Downloads (HF)37
Last updated2024-07-03

Frequently asked questions about llama-3-70B-instruct-uncensored-lora

How much VRAM does llama-3-70B-instruct-uncensored-lora need?

About 3.2 GB at F16 with an 8K context window. That is the 0.0 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 llama-3-70B-instruct-uncensored-lora on an 8 GB GPU?

Yes, with F16: the 0.0 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of llama-3-70B-instruct-uncensored-lora GGUF?

It depends on the quant: F16 is 0.0 GB, F16 is 0.0 GB, F32 is 0.0 GB, F32 is 0.0 GB.

What context length does llama-3-70B-instruct-uncensored-lora support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.

Where can I download llama-3-70B-instruct-uncensored-lora GGUF?

The files are on Hugging Face in the perlets/Dogge-llama-3-70B-instruct-uncensored-lora repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from perlets

All by perlets →

More Llama models

All Llama →

Other tiny models

All tiny models →