GE

Gemma 3 4b Mongolian

GemmaGGUF by mradermacherUpdated 2026-10-02
Download on Hugging Face
Parameters4.55B
Context128K
Layers34
Architecturegemma3
Smallest quant2.0 GB
Quick answer

Gemma 3 4b Mongolian needs about 4.5 GB of memory at Q4_K_M (a 2.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 2.0 GB (Q2_K) to 9.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.

Gemma 3 4b Mongolian – 4.55B parameter chat model trained on curated Mongolian Cyrillic data

Gemma 3 4b Mongolian is a 4.55B parameter model fine‑tuned for grounded answering in Mongolian Cyrillic. It was trained on a hand‑curated corpus of ~2.76B tokens from 25 sources, with 89% Mongolian and 11% English. The model supports a 131072 token context window.

Good at

  • Grounded Mongolian answers
  • Cyrillic language support
  • Citation and uncertainty handling

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is gemma

Best for

  • Mongolian chatbots
  • Localized content generation
  • Research on Cyrillic language models

Who it’s for. Developers building Mongolian language applications who need a chat model that can cite sources and admit uncertainty. Researchers interested in curated, high‑quality Mongolian data may also benefit.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.0 GB 3.6 GB
Fits Get file →
Q3_K_S2.2 GB 3.9 GB
Fits Get file →
Q3_K_M2.4 GB 4.0 GB
Fits Get file →
Q3_K_L2.5 GB 4.2 GB
Fits Get file →
IQ4_XS2.6 GB 4.3 GB
Fits Get file →
Q4_K_S2.8 GB 4.4 GB
Fits Get file →
Q4_K_M2.9 GB 4.5 GB
Fits Get file →
Q5_K_S3.2 GB 4.9 GB
Fits Get file →
Q5_K_M3.3 GB 4.9 GB
Fits Get file →
Q6_K3.7 GB 5.4 GB
Fits Get file →
Q8_04.9 GB 6.5 GB
Fits Get file →
F169.1 GB 10.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (2.88 GB file, ~4.5 GB memory). For 12 GB VRAM, Q5_K_M (3.3 GB file, ~4.9 GB memory). For 16 GB VRAM, Q6_K (3.75 GB file, ~5.4 GB memory).

What GPU do you need for Gemma 3 4b Mongolian?

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 Q3_K_M (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.7 GB file, about 5.4 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.9 GB file, about 6.5 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (9.1 GB file, about 10.8 GB in use).

Which Gemma 3 4b Mongolian quant should you choose?

Q4_K_M is the usual starting point for Gemma 3 4b Mongolian: it balances file size and quality well. Here it is a 2.9 GB file.

The Q8_0 file is 4.9 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 Q2_K at 2.0 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

Architecturegemma3
Parameters4.55B
Layers34
Trained context131,072 tokens
KV cache (fp16)136 KB per token

Source

Quantized bymradermacher
FamilyGemma
Licensegemma
Downloads (HF)748
Last updated2026-10-02

Frequently asked questions about Gemma 3 4b Mongolian

How much VRAM does Gemma 3 4b Mongolian need?

About 4.5 GB at Q4_K_M with an 8K context window. That is the 2.9 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 Gemma 3 4b Mongolian on an 8 GB GPU?

Yes, with Q8_0: the 4.9 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gemma 3 4b Mongolian GGUF?

It depends on the quant: Q2_K is 2.0 GB, Q3_K_S is 2.2 GB, Q3_K_M is 2.4 GB, Q3_K_L is 2.5 GB, IQ4_XS is 2.6 GB, Q4_K_S is 2.8 GB and 6 more.

What context length does Gemma 3 4b Mongolian support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.

Where can I download Gemma 3 4b Mongolian GGUF?

The files are on Hugging Face in the mradermacher/gemma-3-4b-mongolian-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 Gemma 3 4b Mongolian 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?

Yes, the Q4_K_M quant requires about 4.5 GB VRAM at 8k context, which fits in 8 GB.

Does this model support vision?

No, the model has no vision capabilities.

What is the context length?

The model supports a 131072 token context window.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other small models

All small models →