LL

Llama 3.2 3B Instruct

LlamaGGUF by ThomasBaruzierUpdated 2024-10-22
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant0.9 GB
Quick answer

Llama 3.2 3B Instruct needs about 3.5 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 31 quants, from 0.9 GB (IQ1_S) to 6.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Llama 3.2 3B Instruct – a 3.21B parameter instruction‑tuned model

Llama 3.2 3B Instruct is a 3.21B parameter auto‑regressive language model tuned for instruction following. It supports multilingual dialogue and agentic retrieval. The model is available in multiple GGUF quantizations.

Good at

  • Instruction following
  • Multilingual dialogue
  • Agentic retrieval

Limits

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

Best for

  • Chatbots
  • Summarization
  • Code generation

Who it’s for. Developers building instruction‑driven applications who need a lightweight 3B model. The model is suitable for edge deployments with limited VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.9 GB 2.3 GB
Fits Get file →
IQ1_M0.9 GB 2.4 GB
Fits Get file →
IQ2_XXS1.0 GB 2.5 GB
Fits Get file →
IQ2_XS1.1 GB 2.5 GB
Fits Get file →
IQ2_S1.2 GB 2.6 GB
Fits Get file →
IQ2_M1.2 GB 2.7 GB
Fits Get file →
Q2_K_S1.3 GB 2.7 GB
Fits Get file →
IQ3_XXS1.3 GB 2.8 GB
Fits Get file →
Q2_K1.4 GB 2.8 GB
Fits Get file →
IQ3_XS1.5 GB 2.9 GB
Fits Get file →
IQ3_S1.5 GB 3.0 GB
Fits Get file →
Q3_K_S1.5 GB 3.0 GB
Fits Get file →
IQ3_M1.6 GB 3.0 GB
Fits Get file →
Q3_K_M1.7 GB 3.1 GB
Fits Get file →
Q3_K_L1.8 GB 3.3 GB
Fits Get file →
IQ4_XS1.8 GB 3.3 GB
Fits Get file →
Q4_01.9 GB 3.4 GB
Fits Get file →
Q4_01.9 GB 3.4 GB
Fits Get file →
Q4_01.9 GB 3.4 GB
Fits Get file →
IQ4_NL1.9 GB 3.4 GB
Fits Get file →
Q4_01.9 GB 3.4 GB
Fits Get file →
Q4_K_S1.9 GB 3.4 GB
Fits Get file →
Q4_K_M2.0 GB 3.5 GB
Fits Get file →
Q4_12.1 GB 3.5 GB
Fits Get file →
Q5_K_S2.3 GB 3.7 GB
Fits Get file →
Q5_02.3 GB 3.7 GB
Fits Get file →
Q5_K_M2.3 GB 3.8 GB
Fits Get file →
Q5_12.4 GB 3.9 GB
Fits Get file →
Q6_K2.6 GB 4.1 GB
Fits Get file →
Q8_03.4 GB 4.9 GB
Fits Get file →
F166.4 GB 7.9 GB
Tight Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_M (file size 1.92 GB, memory 3.4 GB). For 12 GB VRAM, Q5_K_M (file size 2.32 GB, memory 3.8 GB) or Q6_K (file size 2.64 GB, memory 4.1 GB) are suitable. Higher precision quants like F16 (file size 6.43 GB, memory 7.9 GB) require more memory.

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_1 (2.4 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.9 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.4 GB file, about 7.9 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 2.0 GB file.

The Q8_0 file is 3.4 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 0.9 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
Parameters3.21B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized byThomasBaruzier
FamilyLlama
Licensellama3.2
Downloads (HF)1,044
Last updated2024-10-22

Frequently asked questions about Llama 3.2 3B Instruct

How much VRAM does Llama 3.2 3B Instruct need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.0 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 F16: the 6.4 GB file needs about 7.9 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 0.9 GB, IQ1_M is 0.9 GB, IQ2_XXS is 1.0 GB, IQ2_XS is 1.1 GB, IQ2_S is 1.2 GB, IQ2_M is 1.2 GB and 25 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 ThomasBaruzier/Llama-3.2-3B-Instruct-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 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 Llama 3.2 3B Instruct on 8 GB VRAM?

Yes, use a quant such as Q4_0 or Q4_K_M, which need about 3.4 GB of VRAM at 8k context.

Does this model support vision tasks?

No, the model is text‑only and does not include vision capabilities.

What languages are officially supported?

English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported.

Similar models

Browse all →

More from ThomasBaruzier

All by ThomasBaruzier →

More Llama models

All Llama →

Other tiny models

All tiny models →