ME

Meta Llma 3.2 3B Instruct Paul Graham GGUF

MetaGGUF by dhruvsanganiUpdated 2025-05-19
Download on Hugging Face
Parameters8B
Context128K
Layers32
Architecturellama
Smallest quant4.9 GB
Quick answer

Meta Llma 3.2 3B Instruct Paul Graham GGUF 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. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Meta Llma 3.2 3B Instruct Paul Graham GGUF – 8B parameter llama model

Meta Llma 3.2 3B Instruct Paul Graham GGUF is a llama architecture model with 8B parameters. It was finetuned from unsloth/meta-llama-3.1-8b-instruct-bnb-4bit and trained 2x faster with Unsloth and Huggingface's TRL library. The model supports a context length of 131072 tokens and is released under the apache-2.0 license.

Good at

  • Large context handling
  • Fast finetuning
  • Open source license

Limits

  • No vision support
  • Requires 6.5 GB VRAM at 8 k context
  • Only Q4_K_M quant available

Best for

  • Long-form text generation
  • Research prototyping
  • Educational demos

Who it’s for. Developers and researchers who need a large-context llama model with an open source license. Suitable for those building applications that require up to 131072 tokens of context.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.9 GB 6.5 GB
Fits Get file →

For 8 GB VRAM, use the Q4_K_M quant file (4.92 GB). This provides an approximate memory usage of 6.5 GB at 8 k context. If more VRAM is available, larger quantizations are not listed, so Q4_K_M is the recommended choice.

What GPU do you need for Meta Llma 3.2 3B Instruct Paul Graham GGUF?

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: the best quant that fits is Q4_K_M (4.9 GB file, about 6.5 GB in use).

Which Meta Llma 3.2 3B Instruct Paul Graham GGUF quant should you choose?

Q4_K_M is the usual starting point for Meta Llma 3.2 3B Instruct Paul Graham GGUF: it balances file size and quality well. Here it is a 4.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized bydhruvsangani
FamilyMeta
Licenseapache-2.0
Downloads (HF)1,884
Last updated2025-05-19

Frequently asked questions about Meta Llma 3.2 3B Instruct Paul Graham GGUF

How much VRAM does Meta Llma 3.2 3B Instruct Paul Graham GGUF 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 Llma 3.2 3B Instruct Paul Graham GGUF on an 8 GB GPU?

Yes, with Q4_K_M: the 4.9 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Meta Llma 3.2 3B Instruct Paul Graham GGUF GGUF?

It depends on the quant: Q4_K_M is 4.9 GB.

What context length does Meta Llma 3.2 3B Instruct Paul Graham GGUF support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Meta Llma 3.2 3B Instruct Paul Graham GGUF GGUF?

The files are on Hugging Face in the dhruvsangani/Meta-Llma-3.2-3B-Instruct-Paul-Graham-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 Llma 3.2 3B Instruct Paul Graham GGUF use?

Hugging Face lists the license as apache-2.0. 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 Q4_K_M quant file uses about 6.5 GB at 8 k context, fitting within an 8 GB VRAM budget.

What license does this model use?

The model is released under the apache-2.0 license.

Does this model support vision tasks?

No, the model does not support vision capabilities.

Similar models

Browse all →

More from dhruvsangani

All by dhruvsangani →

More Meta models

All Meta →

Other small models

All small models →