LL

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

LlamaGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters8B
Context8K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

Meta-Llama-3-8B-Instruct-abliterated-v3 needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 21 quants, from 2.0 GB (IQ1_S) to 6.6 GB (Q6_K).

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

Meta-Llama-3-8B-Instruct-abliterated-v3 is a 8B parameter Llama model that has undergone orthogonalization to reduce refusal behavior. It retains the original knowledge base and instruction tuning of the base model. The model supports a 8192 token context window and is released under the llama3 license.

Good at

  • Instruction following
  • Reduced refusal tendencies
  • Large context support

Limits

  • No vision capability
  • Requires 8k context for full performance
  • License restricts commercial use

Best for

  • Chatbots needing fewer refusals
  • Research on refusal mitigation
  • Educational tutoring

Who it’s for. Developers and researchers who need a Llama-3 model with minimized refusal behavior but without extensive fine‑tuning. The model is suitable for applications that require instruction compliance and large context handling.

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_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_K_M4.0 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 →
Q4_04.7 GB 6.2 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XS (2.61 GB, 4.2 GB memory) or Q2_K (3.18 GB, 4.8 GB memory). For 12 GB VRAM, IQ3_XS (3.52 GB, 5.1 GB memory) or Q3_K_S (3.66 GB, 5.2 GB memory) provide a good balance of size and performance. Higher quants such as Q5_K_M (5.73 GB, 7.3 GB memory) are suitable for 16 GB VRAM setups.

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_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).

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

Q4_K_M is the usual starting point for Meta-Llama-3-8B-Instruct-abliterated-v3: it balances file size and quality well. Here it is a 4.9 GB file.

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 bymradermacher
FamilyLlama
Licensellama3
Downloads (HF)2,951
Last updated2024-08-02

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

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

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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_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 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 15 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 mradermacher/Meta-Llama-3-8B-Instruct-abliterated-v3-i1-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, using IQ2_XS or Q2_K quants will fit within 8 GB VRAM with approximate memory usage of 4.2 GB or 4.8 GB respectively.

Does this model support image input?

No, the model has no vision capability.

Is the model fully uncensored?

The model has orthogonalized refusal weights, but it may still provide safety or ethical commentary.

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

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →