LL

Llama 3.1 70B Instruct lorablated

LlamaGGUF by mlabonneUpdated 2024-08-16
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant26.4 GB
Quick answer

Llama 3.1 70B Instruct lorablated needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 4 quants, from 26.4 GB (Q2_K) to 49.9 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Llama 3.1 70B Instruct lorablated – uncensored LoRA‑abliterated model

Llama 3.1 70B Instruct lorablated is a 70.6B parameter model created by merging a LoRA adapter into a censored Llama 3.1. It supports tool usage and retains the original Llama architecture.

Good at

  • Tool integration
  • Uncensored responses
  • Large context handling

Limits

  • No vision support
  • Requires large VRAM for full quant
  • License is llama3.1

Best for

  • Developers building tool‑enabled assistants
  • Researchers testing uncensored LLM behavior
  • Applications needing 70B context depth

Who it’s for. This model is intended for developers and researchers who need a large, uncensored Llama 3.1 variant with tool support. It is suitable for advanced AI projects that can accommodate its memory demands.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K26.4 GB 29.6 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (26.38 GB file, ~29.6 GB memory at 8 k context). For 12 GB VRAM, Q3_K_M (34.27 GB file, ~37.5 GB memory). For 24 GB VRAM, Q4_K_M (42.52 GB file, ~45.7 GB memory).

What GPU do you need for Llama 3.1 70B Instruct lorablated?

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 Q2_K (26.4 GB file, about 29.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 45.7 GB in use).

Which Llama 3.1 70B Instruct lorablated quant should you choose?

Q4_K_M is the usual starting point for Llama 3.1 70B Instruct lorablated: it balances file size and quality well. Here it is a 42.5 GB file.

If memory is tight, the smallest file is Q2_K at 26.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymlabonne
FamilyLlama
Licensellama3.1
Downloads (HF)618
Last updated2024-08-16

Frequently asked questions about Llama 3.1 70B Instruct lorablated

How much VRAM does Llama 3.1 70B Instruct lorablated need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 Llama 3.1 70B Instruct lorablated on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama 3.1 70B Instruct lorablated GGUF?

It depends on the quant: Q2_K is 26.4 GB, Q3_K_M is 34.3 GB, Q4_K_M is 42.5 GB, Q5_K_M is 49.9 GB.

What context length does Llama 3.1 70B Instruct lorablated support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Llama 3.1 70B Instruct lorablated GGUF?

The files are on Hugging Face in the mlabonne/Llama-3.1-70B-Instruct-lorablated-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 Llama 3.1 70B Instruct lorablated use?

Hugging Face lists the license as llama3.1. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, using the Q2_K quantization which requires about 29.6 GB of VRAM at 8 k context, but this exceeds 8 GB, so it is not feasible without further optimization.

Does this model support vision?

No, the model has no vision capabilities.

What license does it use?

The model is licensed under llama3.1.

Other GGUFs of Llama-3.1-70B-Instruct

Similar models

Browse all →

More from mlabonne

All by mlabonne →

More Llama models

All Llama →

Other large models

All large models →