LL

Llama 3.2 1B Intruct Tool Calling V2

LlamaGGUF by nguyenthanhthuanUpdated 2024-10-28
Download on Hugging Face
Parameters1.24B
Context128K
Layers16
Architecturellama
Smallest quant1.3 GB
Quick answer

Llama 3.2 1B Intruct Tool Calling V2 needs about 2.1 GB of memory at Q8_0 (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.

Llama 3.2 1B Instruct Tool Calling V2 – a lightweight function‑calling model

Llama 3.2 1B Instruct Tool Calling V2 is a fine‑tuned version of meta‑llama/Llama‑3.2‑1B‑Instruct. It is optimized for function and tool calling and supports English and Vietnamese. The model is released under Apache 2.0.

Good at

  • Function and tool calling
  • Lightweight inference on modest hardware
  • English and Vietnamese text generation

Limits

  • Requires 8k context for full performance
  • Only Q8_0 quant available
  • No vision or multimodal support

Best for

  • Integrating tool‑calling into applications
  • Rapid prototyping of LLM workflows
  • Running on 8 GB VRAM with Q8_0

Who it’s for. Developers and researchers who need a small, function‑calling capable LLM for English and Vietnamese. The model is suitable for projects that require quick inference and tool integration without large GPU resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_01.3 GB 2.1 GB
Fits Get file →

The single available quant is Q8_0, with a file size of 1.32 GB and an estimated VRAM usage of 2.1 GB at 8k context. This quant is suitable for systems with at least 4 GB of VRAM. No other quants are provided.

What GPU do you need for Llama 3.2 1B Intruct Tool Calling V2?

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 Q8_0 (1.3 GB file, about 2.1 GB in use).

Which Llama 3.2 1B Intruct Tool Calling V2 quant should you choose?

Q8_0 (1.3 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.24B
Layers16
Trained context131,072 tokens
KV cache (fp16)32 KB per token

Source

Quantized bynguyenthanhthuan
FamilyLlama
Licenseapache-2.0
Downloads (HF)635
Last updated2024-10-28

Frequently asked questions about Llama 3.2 1B Intruct Tool Calling V2

How much VRAM does Llama 3.2 1B Intruct Tool Calling V2 need?

About 2.1 GB at Q8_0 with an 8K context window. That is the 1.3 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 1B Intruct Tool Calling V2 on an 8 GB GPU?

Yes, with Q8_0: the 1.3 GB file needs about 2.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 3.2 1B Intruct Tool Calling V2 GGUF?

It depends on the quant: Q8_0 is 1.3 GB.

What context length does Llama 3.2 1B Intruct Tool Calling V2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.

Where can I download Llama 3.2 1B Intruct Tool Calling V2 GGUF?

The files are on Hugging Face in the nguyenthanhthuan/Llama_3.2_1B_Intruct_Tool_Calling_V2 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 1B Intruct Tool Calling V2 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 Q8_0 quant uses approximately 2.1 GB of VRAM at 8k context, leaving headroom for other processes.

Does this model support vision or multimodal inputs?

No, the model only handles text and tool calling; it has no vision capabilities.

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of Llama-3.2-1B-Instruct

Similar models

Browse all →

More from nguyenthanhthuan

All by nguyenthanhthuan →

More Llama models

All Llama →

Other tiny models

All tiny models →