solarized 18B dpo needs about 11.9 GB of memory at Q3_K (a 8.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 6.7 GB (Q2_K) to 10.8 GB (Q4_K).
solarized 18B dpo is a 17.9B-parameter Franken model in GGUF format, quantized by vicgalle. Its trained context length is 4K tokens. The repository has 3 quant files, from 6.7 GB (Q2_K) to 10.8 GB (Q4_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 6.7 GB | 8.5 GB | Too big | Get file → | |
| Q3_K | 8.7 GB | 10.5 GB | Too big | Get file → | |
| Q4_K | 10.8 GB | 12.6 GB | Too big | Get file → |
What GPU do you need for solarized 18B dpo?
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: the best quant that fits is Q3_K (8.7 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K (10.8 GB file, about 14.0 GB in use).
Which solarized 18B dpo quant should you choose?
Q3_K (8.7 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is Q2_K at 6.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about solarized 18B dpo
How much VRAM does solarized 18B dpo need?
About 11.9 GB at Q3_K with an 8K context window. That is the 8.7 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 solarized 18B dpo on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of solarized 18B dpo GGUF?
It depends on the quant: Q2_K is 6.7 GB, Q3_K is 8.7 GB, Q4_K is 10.8 GB.
What context length does solarized 18B dpo support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.4 GB at 4K.
Where can I download solarized 18B dpo GGUF?
The files are on Hugging Face in the vicgalle/solarized-18B-dpo-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 solarized 18B dpo 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.