Ursa Minor F16 needs about 16.2 GB of memory at F16 (a 15.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
Ursa Minor F16 is a 7.62B-parameter Ursa model in GGUF format, quantized by Kaileh57. Its trained context length is 32K tokens. The repository has 1 quant file, from 15.2 GB (F16) to 15.2 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 15.2 GB | 16.2 GB | Too big | Get file → |
What GPU do you need for Ursa Minor F16?
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 F16 (15.2 GB file, about 16.2 GB in use).
Which Ursa Minor F16 quant should you choose?
F16 (15.2 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ursa Minor F16
How much VRAM does Ursa Minor F16 need?
About 16.2 GB at F16 with an 8K context window. That is the 15.2 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 Ursa Minor F16 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ursa Minor F16 GGUF?
It depends on the quant: F16 is 15.2 GB.
What context length does Ursa Minor F16 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download Ursa Minor F16 GGUF?
The files are on Hugging Face in the Kaileh57/Ursa_Minor-F16-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.