KoSOLAR 10.7B v0.4 needs about 23.7 GB of memory at F16 (a 21.6 GB file) with an 8K context window, so it fits on a 24 GB GPU.
KoSOLAR 10.7B v0.4 is a 10.8B-parameter Kosolar model in GGUF format, quantized by Puluming. Its trained context length is 4K tokens. The repository has 1 quant file, from 21.6 GB (F16) to 21.6 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 21.6 GB | 22.9 GB | Too big | Get file → |
What GPU do you need for KoSOLAR 10.7B v0.4?
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 (21.6 GB file, about 23.7 GB in use).
Which KoSOLAR 10.7B v0.4 quant should you choose?
F16 (21.6 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 KoSOLAR 10.7B v0.4
How much VRAM does KoSOLAR 10.7B v0.4 need?
About 23.7 GB at F16 with an 8K context window. That is the 21.6 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 v0.4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 23.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of KoSOLAR 10.7B v0.4 GGUF?
It depends on the quant: F16 is 21.6 GB.
What context length does KoSOLAR 10.7B v0.4 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 v0.4 GGUF?
The files are on Hugging Face in the Puluming/KoSOLAR-10.7B-v0.4 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 v0.4 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.