NbAiLab/borealis2-26b-a4b-preview needs about 25.3 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 6 quants, from 13.3 GB (Q3_K_M) to 50.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
26B‑parameter Gemma‑4 model with Norwegian focus
NbAiLab/borealis2-26b-a4b-preview is a 26B‑parameter instruction‑tuned preview model. It is built on Gemma‑4 and fine‑tuned for Norwegian‑centric tasks. The model is experimental and not safety‑aligned.
Good at
- Norwegian drafting
- Summarization
- Q&A
Limits
- Preview quality; may hallucinate
- Not safety‑aligned
- No vision support
Best for
- Testing Norwegian language models
- Early feedback on Norwegian writing
- Evaluating instruction‑tuning
Who it’s for. Developers and researchers testing Norwegian‑centric LLMs. Use for early evaluation, not production.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 13.3 GB | 21.8 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 25.3 GB | Too big | Get file → | |
| Q5_K_M | 19.1 GB | 27.7 GB | Too big | Get file → | |
| Q6_K | 22.6 GB | 31.2 GB | Too big | Get file → | |
| Q8_0 | 26.9 GB | 35.4 GB | Too big | Get file → | |
| BF16 | 50.5 GB | 59.1 GB | Too big | Get file → |
For 8 GB VRAM, Q3_K_M (13.29 GB) or Q4_K_M (16.8 GB) are suitable. For 16 GB VRAM, Q5_K_M (19.13 GB) or Q6_K (22.64 GB) fit. Larger VRAM allows Q8_0 (26.86 GB) or BF16 (50.51 GB).
What GPU do you need for NbAiLab/borealis2-26b-a4b-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: 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 Q3_K_M (13.3 GB file, about 21.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (22.6 GB file, about 31.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 35.4 GB in use).
Which NbAiLab/borealis2-26b-a4b-preview quant should you choose?
Q4_K_M is the usual starting point for NbAiLab/borealis2-26b-a4b-preview: it balances file size and quality well. Here it is a 16.8 GB file.
The Q8_0 file is 26.9 GB, about 1.6 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 Q3_K_M at 13.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about NbAiLab/borealis2-26b-a4b-preview
How much VRAM does NbAiLab/borealis2-26b-a4b-preview need?
About 25.3 GB at Q4_K_M with an 8K context window. That is the 16.8 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 NbAiLab/borealis2-26b-a4b-preview on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of NbAiLab/borealis2-26b-a4b-preview GGUF?
It depends on the quant: Q3_K_M is 13.3 GB, Q4_K_M is 16.8 GB, Q5_K_M is 19.1 GB, Q6_K is 22.6 GB, Q8_0 is 26.9 GB, BF16 is 50.5 GB.
What context length does NbAiLab/borealis2-26b-a4b-preview support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.
Where can I download NbAiLab/borealis2-26b-a4b-preview GGUF?
The files are on Hugging Face in the NbAiLab/borealis2-26b-a4b-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 NbAiLab/borealis2-26b-a4b-preview use?
Hugging Face lists the license as other. 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?
Use Q3_K_M or Q4_K_M quantizations; they fit within 8 GB VRAM with approximate memory usage of 21.8 GB and 25.3 GB respectively.
Is this model safe for production use?
No. It is a preview experiment and not safety‑aligned; avoid safety‑critical applications.
Does the model support vision tasks?
No. The model only detects vision abilities but does not provide vision inference.