LL

Meta-Llama-3-8B-Instruct-abliterated-v3

LlamaGGUF by failspyUpdated 2024-05-30
Download on Hugging Face
Parameters8B
Context8K
Layers32
Architecturellama
Smallest quant4.0 GB
Quick answer

Meta-Llama-3-8B-Instruct-abliterated-v3 needs about 7.3 GB of memory at its main file (a 5.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 4.0 GB to 16.1 GB.

Meta‑Llama‑3‑8B‑Instruct‑abliterated‑v3 – an 8B instruction model with orthogonalized refusal weights

Meta‑Llama‑3‑8B‑Instruct‑abliterated‑v3 is an 8‑billion‑parameter Llama model trained on 8192‑token context. The weights have been orthogonalized to reduce refusal behavior while keeping other instruction capabilities intact. It is available in GGUF format with several file sizes.

Good at

  • Instruction following
  • Reduced refusal signals
  • Large context handling

Limits

  • No vision support
  • License: llama3
  • No new safety features

Best for

  • Chatbots needing fewer refusals
  • Research on refusal mitigation
  • Fine‑tuning for instruction tasks

Who it’s for. Developers and researchers who want an instruction‑tuned Llama model with minimized refusal behavior. The model is suitable for applications where fewer safety checks are acceptable and the original instruction capabilities are required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—4.0 GB 5.6 GB
Fits Get file →
—4.9 GB 6.5 GB
Fits Get file →
—5.7 GB 7.3 GB
Tight Get file →
—6.6 GB 8.2 GB
Too big Get file →
—8.5 GB 10.1 GB
Too big Get file →
—16.1 GB 17.6 GB
Too big Get file →

The GGUF files range from 4.02 GB to 16.07 GB. For 8 GB VRAM, the 4.92 GB file uses about 6.5 GB of memory at 8 k context. For 16 GB VRAM, the 8.54 GB file uses about 10.1 GB of memory. Choose the smallest file that fits your VRAM budget; memory estimates are approximate.

What GPU do you need for Meta-Llama-3-8B-Instruct-abliterated-v3?

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: the best quant that fits is the main file (4.0 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (8.5 GB file, about 10.1 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (16.1 GB file, about 17.6 GB in use).

Which Meta-Llama-3-8B-Instruct-abliterated-v3 quant should you choose?

If memory is tight, the smallest file is the first one in the table at 4.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byfailspy
FamilyLlama
Licensellama3
Downloads (HF)1,738
Last updated2024-05-30

Frequently asked questions about Meta-Llama-3-8B-Instruct-abliterated-v3

How much VRAM does Meta-Llama-3-8B-Instruct-abliterated-v3 need?

About 7.3 GB at its main file with an 8K context window. That is the 5.7 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 Meta-Llama-3-8B-Instruct-abliterated-v3 on an 8 GB GPU?

Yes, with the smaller files: 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 Meta-Llama-3-8B-Instruct-abliterated-v3 GGUF?

It depends on the quant: file is 4.0 GB, file is 4.9 GB, file is 5.7 GB, file is 6.6 GB, file is 8.5 GB, file is 16.1 GB.

What context length does Meta-Llama-3-8B-Instruct-abliterated-v3 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 Meta-Llama-3-8B-Instruct-abliterated-v3 GGUF?

The files are on Hugging Face in the failspy/Meta-Llama-3-8B-Instruct-abliterated-v3-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 Meta-Llama-3-8B-Instruct-abliterated-v3 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.

Can I run this model on 8 GB VRAM?

Yes, the 4.92 GB GGUF file uses about 6.5 GB of memory at 8 k context, fitting within 8 GB VRAM.

Does this model support vision?

No, it has no vision capabilities.

What license does it use?

The model is licensed under llama3.

Similar models

Browse all →

More from failspy

All by failspy →

More Llama models

All Llama →

Other small models

All small models →