LL

Llama 3.2 3B Thai CRM

LlamaGGUF by yothinSUpdated 2026-10-07
Download on Hugging Face
Parameters3.2B
Context128K
Layers28
Architecturellama
Smallest quant1.4 GB
Quick answer

Llama 3.2 3B Thai CRM needs about 3.8 GB of memory at its main file (a 2.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 1.4 GB 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 Thai CRM – fine‑tuned for Thai customer relationship management

Llama 3.2 3B Thai CRM is a 3.2‑billion parameter causal language model trained for CRM workflows in Thai and English. It supports context lengths up to 131072 tokens and is released under the Llama 3.2 Community License.

Good at

  • CRM chatbot in Thai and English
  • Customer behavior analysis
  • Retention strategy suggestions

Limits

  • No vision support
  • Requires human oversight for legal or billing queries
  • May hallucinate outside CRM domain

Best for

  • CRM query routing
  • Customer feedback analysis
  • Retention campaign drafting

Who it’s for. Developers building Thai‑language CRM assistants or analytics tools. Ideal for businesses needing localized customer support and behavioral insights.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.4 GB 2.8 GB
Fits Get file →
—1.7 GB 3.1 GB
Fits Get file →
—2.0 GB 3.5 GB
Fits Get file →
—2.3 GB 3.8 GB
Fits Get file →
—2.6 GB 4.1 GB
Fits Get file →
—3.4 GB 4.9 GB
Fits Get file →
F166.4 GB 7.9 GB
Tight Get file →

For 8 GB VRAM, use the 1.36 GB file (est. 2.8 GB memory at 8 k context). For 12 GB VRAM, the 2.02 GB file (est. 3.5 GB memory) is suitable. The 6.43 GB F16 file requires at least 8 GB VRAM and is best for higher accuracy.

What GPU do you need for Llama 3.2 3B Thai CRM?

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 the main file (2.3 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (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 Thai CRM quant should you choose?

If memory is tight, the smallest file is the first one in the table at 1.4 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.2B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized byyothinS
FamilyLlama
Licensellama3.2
Downloads (HF)106
Last updated2026-10-07

Frequently asked questions about Llama 3.2 3B Thai CRM

How much VRAM does Llama 3.2 3B Thai CRM need?

About 3.8 GB at its main file with an 8K context window. That is the 2.3 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 3B Thai CRM 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 Thai CRM GGUF?

It depends on the quant: file is 1.4 GB, file is 1.7 GB, file is 2.0 GB, file is 2.3 GB, file is 2.6 GB, file is 3.4 GB and 1 more.

What context length does Llama 3.2 3B Thai CRM 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 Thai CRM GGUF?

The files are on Hugging Face in the yothinS/Llama-3.2-3B-Thai-CRM-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 Thai CRM 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 this model on 8 GB VRAM?

Yes, the 1.36 GB quantized file uses about 2.8 GB memory at 8 k context, fitting within 8 GB VRAM.

Does the model support image input?

No, the model has no vision capabilities.

What license applies to this model?

It is released under the Llama 3.2 Community License.

Similar models

Browse all →

More from yothinS

All by yothinS →

More Llama models

All Llama →

Other tiny models

All tiny models →