Borealis 27b Instruct Preview needs about 22.0 GB of memory at Q4_K_M (a 17.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 17.3 GB (Q4_K_M) to 56.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.
Borealis 27b Instruct Preview is a 28.4B-parameter Borealis model in GGUF format, quantized by NbAiLab. Its trained context length is 128K tokens. The repository has 3 quant files, from 17.3 GB (Q4_K_M) to 56.8 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 17.3 GB | 22.0 GB | Too big | Get file → | |
| Q8_0 | 30.2 GB | 34.9 GB | Too big | Get file → | |
| BF16 | 56.8 GB | 61.5 GB | Too big | Get file → |
What GPU do you need for Borealis 27b 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: 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 Q4_K_M (17.3 GB file, about 22.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (17.3 GB file, about 22.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (30.2 GB file, about 34.9 GB in use).
Which Borealis 27b Instruct Preview quant should you choose?
Q4_K_M is the usual starting point for Borealis 27b Instruct Preview: it balances file size and quality well. Here it is a 17.3 GB file.
The Q8_0 file is 30.2 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
Source
Frequently asked questions about Borealis 27b Instruct Preview
How much VRAM does Borealis 27b Instruct Preview need?
About 22.0 GB at Q4_K_M with an 8K context window. That is the 17.3 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 27b Instruct Preview on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Borealis 27b Instruct Preview GGUF?
It depends on the quant: Q4_K_M is 17.3 GB, Q8_0 is 30.2 GB, BF16 is 56.8 GB.
What context length does Borealis 27b 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 4.2 GB at 8K and 16.6 GB at 32K.
Where can I download Borealis 27b Instruct Preview GGUF?
The files are on Hugging Face in the NbAiLab/borealis-27b-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 27b 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.