LL

Llama 3.2 3B Instruct

LlamaGGUF by brittlewis12Updated 2024-09-27
Download on Hugging Face
Parameters3.61B
Context128K
Layers28
Architecturellama
Smallest quant1.0 GB
Quick answer

Llama 3.2 3B Instruct 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. This repository has 24 quants, from 1.0 GB (IQ1_S) to 7.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Llama 3.2 3B Instruct – 3.61 B parameters, 131072‑token context

Llama 3.2 3B Instruct is a 3.61 B parameter model with a 131072‑token training context. It is available in multiple GGUF quantizations ranging from IQ1_S to F16. The model supports instruction following and general-purpose text generation.

Good at

  • Instruction following
  • Short‑form content creation
  • Context‑aware dialogue

Limits

  • No vision support
  • License not specified
  • Large context requires significant VRAM

Best for

  • Chatbots with limited GPU memory
  • Rapid prototyping of instruction models
  • Educational demos

Who it’s for. Developers and researchers needing a lightweight instruction model for local deployment. Suitable for environments with modest GPU resources and no need for vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.0 GB 2.4 GB
Fits Get file →
IQ1_M1.1 GB 2.5 GB
Fits Get file →
IQ2_XXS1.1 GB 2.6 GB
Fits Get file →
IQ2_XS1.2 GB 2.7 GB
Fits Get file →
IQ2_S1.3 GB 2.8 GB
Fits Get file →
IQ2_M1.4 GB 2.8 GB
Fits Get file →
Q2_K_S1.4 GB 2.8 GB
Fits Get file →
Q2_K1.5 GB 2.9 GB
Fits Get file →
IQ3_XXS1.5 GB 3.0 GB
Fits Get file →
IQ3_XS1.6 GB 3.1 GB
Fits Get file →
Q3_K_S1.7 GB 3.2 GB
Fits Get file →
IQ3_S1.7 GB 3.2 GB
Fits Get file →
IQ3_M1.8 GB 3.2 GB
Fits Get file →
Q3_K_M1.9 GB 3.3 GB
Fits Get file →
Q3_K_L2.0 GB 3.4 GB
Fits Get file →
IQ4_XS2.0 GB 3.5 GB
Fits Get file →
IQ4_NL2.1 GB 3.6 GB
Fits Get file →
Q4_K_S2.1 GB 3.6 GB
Fits Get file →
Q4_K_M2.2 GB 3.7 GB
Fits Get file →
Q5_K_S2.5 GB 4.0 GB
Fits Get file →
Q5_K_M2.6 GB 4.0 GB
Fits Get file →
Q6_K3.0 GB 4.4 GB
Fits Get file →
Q8_03.8 GB 5.3 GB
Fits Get file →
F167.2 GB 8.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.24 GB, estimated 3.7 GB memory). If 12 GB VRAM is available, Q5_K_M (2.59 GB, 4 GB memory) offers better quality. For 16 GB VRAM, Q6_K (2.97 GB, 4.4 GB memory) or Q8_0 (3.84 GB, 5.3 GB memory) are viable options.

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

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 Q5_K_M (2.6 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.8 GB file, about 5.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.8 GB file, about 5.3 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (7.2 GB file, about 8.7 GB in use).

Which Llama 3.2 3B Instruct quant should you choose?

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

The Q8_0 file is 3.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ1_S at 1.0 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
Parameters3.61B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized bybrittlewis12
FamilyLlama
Downloads (HF)841
Last updated2024-09-27

Frequently asked questions about Llama 3.2 3B Instruct

How much VRAM does Llama 3.2 3B Instruct 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 on an 8 GB GPU?

Yes, with Q8_0: the 3.8 GB file needs about 5.3 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 GGUF?

It depends on the quant: IQ1_S is 1.0 GB, IQ1_M is 1.1 GB, IQ2_XXS is 1.1 GB, IQ2_XS is 1.2 GB, IQ2_S is 1.3 GB, IQ2_M is 1.4 GB and 18 more.

What context length does Llama 3.2 3B Instruct 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 GGUF?

The files are on Hugging Face in the brittlewis12/Llama-3.2-3B-Instruct-uncensored-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Llama 3.2 3B Instruct on 8 GB VRAM?

Yes, using Q4_K_M or Q4_K_S quantizations requires approximately 3.6–3.7 GB of VRAM at 8 k context.

What is the smallest quantization file?

IQ1_S is the smallest at 1 GB, estimating 2.4 GB VRAM usage at 8 k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

Similar models

Browse all →

More from brittlewis12

All by brittlewis12 →

More Llama models

All Llama →

Other small models

All small models →