GE

BgGPT Gemma 3 27B IT

GemmaGGUF by INSAIT-InstituteUpdated 2026-03-25
Download on Hugging Face
Parameters27B
Context128K
Layers62
Architecturegemma3
Smallest quant16.5 GB
Quick answer

BgGPT Gemma 3 27B IT needs about 21.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 16.5 GB (Q4_K_M) to 28.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.

BgGPT Gemma 3 27B IT – 27 B parameter LLM with vision and long‑context support

BgGPT Gemma 3 27B IT is a 27 B parameter language model based on Gemma 3, adapted for Bulgarian. It supports vision‑language understanding and a 131 k token context window. The model is available in several GGUF quantizations for llama.cpp and other GGUF tools.

Good at

  • Vision‑language tasks
  • Long‑context conversations
  • Instruction following

Limits

  • Large VRAM requirement (≈21 GB for Q4_K_M at 8 k context)
  • No separate vision hardware needed – runs on GPU with compute capability ≥8.9
  • License restricted to Gemma Terms of Use

Best for

  • Multimodal chatbots
  • Long‑form content generation
  • Complex instruction handling

Who it’s for. Developers building multilingual or Bulgarian‑focused applications that need both text and image understanding. Suitable for research or production environments with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M16.5 GB 21.2 GB
Too big Get file →
Q5_K_M19.3 GB 23.9 GB
Too big Get file →
Q6_K22.2 GB 26.8 GB
Too big Get file →
Q8_028.7 GB 33.4 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (file size 16.55 GB, estimated 21.2 GB memory at 8 k context). With 12 GB VRAM Q5_K_M (19.27 GB, 23.9 GB memory) is feasible. Larger GPUs can run Q6_K or Q8_0 for higher precision.

What GPU do you need for BgGPT Gemma 3 27B IT?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.3 GB file, about 23.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.2 GB file, about 26.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (28.7 GB file, about 33.4 GB in use).

Which BgGPT Gemma 3 27B IT quant should you choose?

Q4_K_M is the usual starting point for BgGPT Gemma 3 27B IT: it balances file size and quality well. Here it is a 16.5 GB file.

The Q8_0 file is 28.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters27B
Layers62
Trained context131,072 tokens
KV cache (fp16)496 KB per token

Source

Quantized byINSAIT-Institute
FamilyGemma
Licensegemma
Downloads (HF)7,533
Last updated2026-03-25

Frequently asked questions about BgGPT Gemma 3 27B IT

How much VRAM does BgGPT Gemma 3 27B IT need?

About 21.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 BgGPT Gemma 3 27B IT on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of BgGPT Gemma 3 27B IT GGUF?

It depends on the quant: Q4_K_M is 16.5 GB, Q5_K_M is 19.3 GB, Q6_K is 22.2 GB, Q8_0 is 28.7 GB.

What context length does BgGPT Gemma 3 27B IT support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.

Where can I download BgGPT Gemma 3 27B IT GGUF?

The files are on Hugging Face in the INSAIT-Institute/BgGPT-Gemma-3-27B-IT-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 BgGPT Gemma 3 27B IT 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 BgGPT Gemma 3 27B IT on 8 GB VRAM?

No, the smallest quantization requires about 21 GB VRAM at 8 k context. You would need a GPU with at least 24 GB VRAM.

Does the model support image input?

Yes, the model has vision-language understanding and can process images within the same context.

What is the effective context length?

The model supports up to 131,072 tokens, enabling long conversations and complex instructions.

Other GGUFs of BgGPT-Gemma-3-27B-IT

Similar models

Browse all →

More from INSAIT-Institute

All by INSAIT-Institute →

More Gemma models

All Gemma →

Other medium models

All medium models →