LL

Llama 3.2 3B Instruct Abliterated

LlamaGGUF by Hasaranga85Updated 2024-10-08
Download on Hugging Face
Parameters3.61B
Context128K
Layers28
Architecturellama
Smallest quant2.2 GB
Quick answer

Llama 3.2 3B Instruct Abliterated needs about 3.7 GB of memory at Q4_K_M (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Llama 3.2 3B Instruct Abliterated – 3.61 B parameters, 131072 context

Llama 3.2 3B Instruct Abliterated is a 3.61 B parameter model with a 131072 token context window. It is an uncensored, abliterated version of Llama‑3.2‑3B‑Instruct. The model is available in a Q4_K_M quantized GGUF file of 2.24 GB.

Good at

  • Large context handling
  • Uncensored instruction following
  • Low‑memory inference

Limits

  • No vision support
  • Requires 8 k context for memory estimate
  • License: llama3.2

Best for

  • Chatbot development
  • Instruction‑based applications
  • Low‑resource inference

Who it’s for. Developers needing a small, low‑memory Llama model with a large context window. Suitable for local deployment on devices with limited VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.2 GB 3.7 GB
Fits Get file →

The Q4_K_M quantized file is 2.24 GB and requires about 3.7 GB of RAM at 8 k context. This is the only quant available, so use it if your memory budget allows. For tighter budgets, no other quant is provided.

What GPU do you need for Llama 3.2 3B Instruct Abliterated?

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 Q4_K_M (2.2 GB file, about 3.7 GB in use).

Which Llama 3.2 3B Instruct Abliterated quant should you choose?

Q4_K_M is the usual starting point for Llama 3.2 3B Instruct Abliterated: it balances file size and quality well. Here it is a 2.2 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.61B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized byHasaranga85
FamilyLlama
Licensellama3.2
Downloads (HF)2,241
Last updated2024-10-08

Frequently asked questions about Llama 3.2 3B Instruct Abliterated

How much VRAM does Llama 3.2 3B Instruct Abliterated need?

About 3.7 GB at Q4_K_M with an 8K context window. That is the 2.2 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 3.2 3B Instruct Abliterated on an 8 GB GPU?

Yes, with Q4_K_M: the 2.2 GB file needs about 3.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 3.2 3B Instruct Abliterated GGUF?

It depends on the quant: Q4_K_M is 2.2 GB.

What context length does Llama 3.2 3B Instruct Abliterated support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download Llama 3.2 3B Instruct Abliterated GGUF?

The files are on Hugging Face in the Hasaranga85/Llama-3.2-3B-Instruct-abliterated-Q4_K_M-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 3.2 3B Instruct Abliterated use?

Hugging Face lists the license as llama3.2. 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?

The Q4_K_M quant requires about 3.7 GB of RAM at 8 k context, so it can run on a system with 8 GB VRAM, but performance may be limited.

Does this model support vision?

No, the model has no vision capabilities.

What license applies to this model?

The model is licensed under llama3.2.

Other GGUFs of Llama-3.2-3B-Instruct-abliterated

Similar models

Browse all →

More from Hasaranga85

All by Hasaranga85 →

More Llama models

All Llama →

Other small models

All small models →