LL

Llama 3.2 3B Instruct

LlamaGGUF by Chemin-AIUpdated 2024-11-27
Download on Hugging Face
Parameters3.61B
Context128K
Layers28
Architecturellama
Smallest quant1.7 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 13 quants, from 1.7 GB (Q3_K_S) to 3.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Llama 3.2 3B Instruct is a 3.61B-parameter Llama model in GGUF format, quantized by Chemin-AI. Its trained context length is 128K tokens. The repository has 13 quant files, from 1.7 GB (Q3_K_S) to 3.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S1.7 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 →
Q4_02.1 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 →
Q4_12.3 GB 3.8 GB
Fits Get file →
Q5_02.5 GB 4.0 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 →
Q5_12.7 GB 4.2 GB
Fits Get file →
Q6_K3.0 GB 4.4 GB
Fits Get file →
Q8_03.8 GB 5.3 GB
Fits Get file →

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).

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 Q3_K_S at 1.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 byChemin-AI
FamilyLlama
Downloads (HF)380
Last updated2024-11-27

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: Q3_K_S is 1.7 GB, Q3_K_M is 1.9 GB, Q3_K_L is 2.0 GB, Q4_0 is 2.1 GB, Q4_K_S is 2.1 GB, Q4_K_M is 2.2 GB and 7 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 Chemin-AI/malaysian-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.

Other GGUFs of Malaysian-Llama-3.2-3B-Instruct-v0.1

Similar models

Browse all →

More from Chemin-AI

All by Chemin-AI →

More Llama models

All Llama →

Other small models

All small models →