LL

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

LlamaGGUF by legraphistaUpdated 2024-06-01
Download on Hugging Face
Parameters8B
Context8K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

Meta-Llama-3-8B-Instruct-abliterated-v3 needs about 5.4 GB of memory at IQ3_M (a 3.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 2.0 GB (IQ1_S) to 16.1 GB.

Meta‑Llama‑3‑8B‑Instruct‑abliterated‑v3: 8B Llama model with orthogonalized refusal weights

This 8‑billion‑parameter Llama model has been orthogonalized to reduce refusal behavior while preserving original knowledge. It supports a 8192‑token context window and is released under the llama3 license. The model is available in multiple GGUF quantizations.

Good at

  • Reduced refusal responses
  • Maintains original instruction behavior
  • Supports 8192‑token context

Limits

  • No vision or multimodal support
  • Requires at least 3.6 GB VRAM for IQ1_S at 8K context
  • License is llama3, not permissive

Best for

  • Chat applications needing low refusal
  • Fine‑tuning on top of a stable base
  • Running on moderate‑end GPUs

Who it’s for. Developers and researchers who need an instruction‑tuned Llama model with minimized refusal behavior. The model is suitable for local inference on systems with sufficient VRAM and a compatible llama.cpp setup.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.0 GB 3.6 GB
Fits Get file →
IQ1_M2.2 GB 3.7 GB
Fits Get file →
IQ2_XXS2.4 GB 4.0 GB
Fits Get file →
IQ2_XS2.6 GB 4.2 GB
Fits Get file →
IQ2_S2.8 GB 4.3 GB
Fits Get file →
IQ2_M2.9 GB 4.5 GB
Fits Get file →
Q2_K_S3.0 GB 4.6 GB
Fits Get file →
Q2_K3.2 GB 4.8 GB
Fits Get file →
IQ3_XXS3.3 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.4 GB 6.0 GB
Fits Get file →
IQ4_NL4.7 GB 6.3 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K4.9 GB 6.5 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →
BF1616.1 GB 17.6 GB
Too big Get file →
—16.1 GB 17.6 GB
Too big Get file →

For 8 GB VRAM, use IQ2_S (4.3 GB file, ~4.3 GB VRAM at 8K context). For 12 GB VRAM, Q4_K (6.5 GB VRAM estimate) or Q5_K_S (7.2 GB VRAM estimate) provide a balance of size and quality. Higher quants like Q8_0 require >10 GB VRAM.

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: the best quant that fits is IQ2_XXS (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K (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 Meta-Llama-3-8B-Instruct-abliterated-v3 quant should you choose?

IQ3_M (3.8 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 2.0 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
Parameters8B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bylegraphista
FamilyLlama
Licensellama3
Downloads (HF)4,389
Last updated2024-06-01

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

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

About 5.4 GB at IQ3_M with an 8K context window. That is the 3.8 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 Q5_K: 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: IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB, IQ2_M is 2.9 GB and 19 more.

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 legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-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 IQ2_S quant uses about 4.3 GB VRAM at 8K context, fitting within an 8 GB GPU.

Does this model support vision or multimodal inputs?

No, the model has no vision or multimodal capabilities.

What license applies to this model?

The model is released under the llama3 license, which is not permissive.

Other GGUFs of Meta-Llama-3-8B-Instruct-abliterated-v3

Similar models

Browse all →

More from legraphista

All by legraphista →

More Llama models

All Llama →

Other small models

All small models →