microsoft.Fara1.5 27B needs about 19.2 GB of memory at F16 (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 10.7 GB (F16) to 28.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
microsoft.Fara1.5 27B is a 26.9B-parameter Fara model in GGUF format, quantized by DevQuasar. Its trained context length is 256K tokens. The repository has 6 quant files, from 10.7 GB (F16) to 28.6 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 10.7 GB | 13.4 GB | Too big | Get file → | |
| F16 | 13.3 GB | 15.9 GB | Too big | Get file → | |
| F16 | 16.5 GB | 19.2 GB | Too big | Get file → | |
| F16 | 19.2 GB | 21.9 GB | Too big | Get file → | |
| F16 | 22.1 GB | 24.7 GB | Too big | Get file → | |
| F16 | 28.6 GB | 31.2 GB | Too big | Get file → |
What GPU do you need for microsoft.Fara1.5 27B?
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: the best quant that fits is F16 (13.3 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (19.2 GB file, about 21.9 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (28.6 GB file, about 31.2 GB in use).
Which microsoft.Fara1.5 27B quant should you choose?
F16 (16.5 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is F16 at 10.7 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about microsoft.Fara1.5 27B
How much VRAM does microsoft.Fara1.5 27B need?
About 19.2 GB at F16 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 microsoft.Fara1.5 27B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of microsoft.Fara1.5 27B GGUF?
It depends on the quant: F16 is 10.7 GB, F16 is 13.3 GB, F16 is 16.5 GB, F16 is 19.2 GB, F16 is 22.1 GB, F16 is 28.6 GB.
What context length does microsoft.Fara1.5 27B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download microsoft.Fara1.5 27B GGUF?
The files are on Hugging Face in the DevQuasar/microsoft.Fara1.5-27B-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 microsoft.Fara1.5 27B use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.