KoSOLAR 10.7B v0.2 finetuned needs about 8.0 GB of memory at IQ4_XS (a 5.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 5.9 GB (IQ4_XS) to 7.7 GB (Q5_K_M).
KoSOLAR 10.7B v0.2 finetuned is a 10.8B-parameter Kosolar model in GGUF format, quantized by jjlee6496. Its trained context length is 4K tokens. The repository has 2 quant files, from 5.9 GB (IQ4_XS) to 7.7 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 5.9 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_M | 7.7 GB | 9.0 GB | Too big | Get file → |
What GPU do you need for KoSOLAR 10.7B v0.2 finetuned?
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: the best quant that fits is IQ4_XS (5.9 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (7.7 GB file, about 9.8 GB in use).
Which KoSOLAR 10.7B v0.2 finetuned quant should you choose?
IQ4_XS (5.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about KoSOLAR 10.7B v0.2 finetuned
How much VRAM does KoSOLAR 10.7B v0.2 finetuned need?
About 8.0 GB at IQ4_XS with an 8K context window. That is the 5.9 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 KoSOLAR 10.7B v0.2 finetuned on an 8 GB GPU?
Yes, with IQ4_XS: the 5.9 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of KoSOLAR 10.7B v0.2 finetuned GGUF?
It depends on the quant: IQ4_XS is 5.9 GB, Q5_K_M is 7.7 GB.
What context length does KoSOLAR 10.7B v0.2 finetuned support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.
Where can I download KoSOLAR 10.7B v0.2 finetuned GGUF?
The files are on Hugging Face in the jjlee6496/KoSOLAR-10.7B-v0.2-finetuned-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 KoSOLAR 10.7B v0.2 finetuned use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.