BU

ai4burmese padauk

BurmeseGGUF by WYNN747Updated 2026-04-18
Download on Hugging Face
Parameters7.46B
Context128K
Layers42
Architecturegemma4
Smallest quant8.0 GB
Quick answer

ai4burmese padauk needs about 9.9 GB of memory at Q8_0 (a 8.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

AI4Burmese Padauk – a Burmese‑first, agentic small language model

AI4Burmese Padauk is a 7.46 billion‑parameter Gemma 4 model quantized to Q8_0. It is designed for local inference via Ollama, llama.cpp, and OpenAI‑compatible APIs, with a focus on Burmese context understanding and tool‑enabled assistant workflows.

Good at

  • Burmese‑first language understanding
  • Agentic tool‑calling
  • Local inference on edge devices

Limits

  • Requires 9.9 GB VRAM at 8 k context
  • Only Q8_0 quant available
  • License: gemma

Best for

  • Burmese local assistants
  • MCP workflows
  • Edge deployment

Who it’s for. Developers, students, and researchers building Burmese‑centric AI assistants or tools that need local inference without cloud dependence.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_08.0 GB 9.9 GB
Too big Get file →

The only available quant is Q8_0, file size 7.97 GB. It needs approximately 9.9 GB VRAM at 8 k context. For lower memory budgets, no other quant is provided.

What GPU do you need for ai4burmese padauk?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.9 GB in use).

Which ai4burmese padauk quant should you choose?

Q8_0 (8.0 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

Architecturegemma4
Parameters7.46B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized byWYNN747
FamilyBurmese
Licensegemma
Downloads (HF)248
Last updated2026-04-18

Frequently asked questions about ai4burmese padauk

How much VRAM does ai4burmese padauk need?

About 9.9 GB at Q8_0 with an 8K context window. That is the 8.0 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 ai4burmese padauk on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ai4burmese padauk GGUF?

It depends on the quant: Q8_0 is 8.0 GB.

What context length does ai4burmese padauk support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download ai4burmese padauk GGUF?

The files are on Hugging Face in the WYNN747/ai4burmese-padauk-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 ai4burmese padauk use?

Hugging Face lists the license as gemma. 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?

No, the model requires about 9.9 GB VRAM at 8 k context.

What runtimes support this model?

Ollama, llama.cpp, and OpenAI‑compatible local APIs.

Does it support vision tasks?

No vision support is provided.

Similar models

Browse all →

More from WYNN747

All by WYNN747 →

More Burmese models

All Burmese →

Other small models

All small models →