BO

Borealis 4b Instruct Preview

BorealisGGUF by NbAiLabUpdated 2026-02-20
Download on Hugging Face
Parameters3.88B
Context128K
Layers34
Architecturegemma3
Smallest quant2.5 GB
Quick answer

Borealis 4b Instruct Preview needs about 4.1 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.5 GB (Q4_K_M) to 7.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.

Borealis 4b Instruct Preview is a 3.88B-parameter Borealis model in GGUF format, quantized by NbAiLab. Its trained context length is 128K tokens. The repository has 3 quant files, from 2.5 GB (Q4_K_M) to 7.8 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.5 GB 4.1 GB
Fits Get file →
Q8_04.1 GB 5.8 GB
Fits Get file →
BF167.8 GB 9.4 GB
Too big Get file →

What GPU do you need for Borealis 4b Instruct Preview?

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: the best quant that fits is Q8_0 (4.1 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.8 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (7.8 GB file, about 9.4 GB in use).

Which Borealis 4b Instruct Preview quant should you choose?

Q4_K_M is the usual starting point for Borealis 4b Instruct Preview: it balances file size and quality well. Here it is a 2.5 GB file.

The Q8_0 file is 4.1 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
Parameters3.88B
Layers34
Trained context131,072 tokens
KV cache (fp16)136 KB per token

Source

Quantized byNbAiLab
FamilyBorealis
Licensegemma
Downloads (HF)173
Last updated2026-02-20

Frequently asked questions about Borealis 4b Instruct Preview

How much VRAM does Borealis 4b Instruct Preview need?

About 4.1 GB at Q4_K_M with an 8K context window. That is the 2.5 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 Borealis 4b Instruct Preview on an 8 GB GPU?

Yes, with Q8_0: the 4.1 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Borealis 4b Instruct Preview GGUF?

It depends on the quant: Q4_K_M is 2.5 GB, Q8_0 is 4.1 GB, BF16 is 7.8 GB.

What context length does Borealis 4b Instruct Preview 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 Borealis 4b Instruct Preview GGUF?

The files are on Hugging Face in the NbAiLab/borealis-4b-instruct-preview-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 Borealis 4b Instruct Preview 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.

Similar models

Browse all →

More from NbAiLab

All by NbAiLab →

More Borealis models

All Borealis →

Other small models

All small models →