license: apache-2.0
tags:
- requests
- gguf
- quantized
Quant-Requests are open.
I apologize for disrupting your experience.
If you want and you are able to...
You can support my various endeavors here (Ko-fi).
Eventually I want to have a proper infrastructure for these.
In the meantime I'll be working to make do with the resources at hand at the time.
Welcome to my GGUF-IQ-Imatrix Model Quantization Requests card!
Please read everything.
This card is meant only to request GGUF-IQ-Imatrix quants for models that meet the requirements bellow.
Requirements to request GGUF-Imatrix model quantizations:
For the model:
- Maximum model parameter size of 11B.
At the moment I am unable to accept requests for larger models due to hardware/time limitations.
Preferably for Mistral and LLama-3 based models in the creative/roleplay niche.
If you need a bigger model, you can try requesting at mradermacher's. Pretty awesome.
Important:
- Fill the request template as outlined in the next section.
How to request a model quantization:
Open a New Discussion titled "
Request: Model-Author/Model-Name
", for example, "Request: Nitral-AI/Infinitely-Laydiculous-7B
", without the quotation marks.Include the following template in your post and fill the required information (example request here):
**[Required] Model name:**
**[Required] Model link:**
**[Required] Brief description:**
**[Required] An image/direct image link to represent the model (square shaped):**
**[Optional] Additonal quants (if you want any):**
<!-- Keep in mind that anything bellow I/Q3 isn't recommended, -->
<!-- since for these smaller models the results will likely be -->
<!-- highly incoherent rendering them unusable for your needs. -->
Default list of quants for reference:
"IQ3_M", "IQ3_XXS",
"Q4_K_M", "Q4_K_S", "IQ4_XS",
"Q5_K_M", "Q5_K_S",
"Q6_K",
"Q8_0"