LL

Llama-3.2-3B-Instruct

LlamaGGUF by unslothUpdated 2025-11-08
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 27 quants, from 0.9 GB (IQ1_S) to 6.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Llama‑3.2‑3B‑Instruct – 3 billion‑parameter instruction‑tuned model

Llama‑3.2‑3B‑Instruct is a 3 billion‑parameter, instruction‑tuned Llama model. It supports 131 072‑token context and is available in multiple GGUF quantisations. The model is trained for multilingual dialogue and summarisation tasks.

Good at

  • Multilingual dialogue
  • Instruction following
  • Summarisation

Limits

  • Large context size requires significant VRAM
  • No vision or multimodal support
  • License is llama3.2

Best for

  • Chatbots on low‑VRAM GPUs
  • Fine‑tuning for specific domains
  • Rapid prototyping of instruction‑tuned models

Who it’s for. Developers and researchers who need a lightweight, instruction‑tuned Llama model for text‑only applications. The model is suitable for those who prefer open‑source, multilingual LLMs with a moderate parameter count.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.9 GB 2.4 GB
Fits Get file →
IQ1_M1.0 GB 2.4 GB
Fits Get file →
IQ2_XXS1.0 GB 2.5 GB
Fits Get file →
IQ2_M1.3 GB 2.7 GB
Fits Get file →
Q2_K1.4 GB 2.8 GB
Fits Get file →
Q2_K_L1.4 GB 2.8 GB
Fits Get file →
IQ3_XXS1.4 GB 2.8 GB
Fits Get file →
Q2_K_XL1.4 GB 2.8 GB
Fits Get file →
Q3_K_S1.5 GB 3.0 GB
Fits Get file →
Q3_K_M1.7 GB 3.1 GB
Fits Get file →
Q3_K_XL1.7 GB 3.2 GB
Fits Get file →
IQ4_XS1.8 GB 3.3 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_K_XL2.1 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_K_M2.3 GB 3.8 GB
Fits Get file →
Q5_K_XL2.3 GB 3.8 GB
Fits Get file →
Q6_K2.6 GB 4.1 GB
Fits Get file →
Q6_K_XL3.0 GB 4.4 GB
Fits Get file →
Q8_03.4 GB 4.9 GB
Fits Get file →
Q8_K_XL4.2 GB 5.6 GB
Fits Get file →
F166.4 GB 7.9 GB
Tight Get file →
BF166.4 GB 7.9 GB
Tight Get file →

For 8 GB VRAM, use Q4_K_M (2.02 GB file, ~3.5 GB VRAM at 8 k context). For 12 GB VRAM, Q5_K_M (2.32 GB file, ~3.8 GB VRAM). For 16 GB VRAM, Q6_K (2.64 GB file, ~4.1 GB VRAM).

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_XL (2.3 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_K_XL (4.2 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (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 byunsloth
FamilyLlama
Licensellama3.2
Downloads (HF)165,427
Last updated2025-11-08

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 BF16: 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 1.0 GB, IQ2_XXS is 1.0 GB, IQ2_M is 1.3 GB, Q2_K is 1.4 GB, Q2_K_L is 1.4 GB and 21 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 unsloth/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, with a 4‑bit quantisation such as Q4_K_M, which uses about 3.5 GB VRAM at 8 k context.

Does this model support image input?

No, it is a text‑only model with no vision capabilities.

What license applies to this model?

The model is licensed under the llama3.2 license.

Other GGUFs of Llama-3.2-3B-Instruct

Similar models

Browse all →

More from unsloth

All by unsloth →

More Llama models

All Llama →

Other tiny models

All tiny models →