Quantization made by Richard Erkhov.

Github

Discord

Request more models

Replete-Qwen-2.5-3b-CoT-RP - GGUF

• Model creator: https://huggingface.co/bunnycore/
• Original model: https://huggingface.co/bunnycore/Replete-Qwen-2.5-3b-CoT-RP/

Name	Quant method	Size
Replete-Qwen-2.5-3b-CoT-RP.Q2_K.gguf	Q2_K	1.28GB
Replete-Qwen-2.5-3b-CoT-RP.IQ3_XS.gguf	IQ3_XS	1.42GB
Replete-Qwen-2.5-3b-CoT-RP.IQ3_S.gguf	IQ3_S	1.48GB
Replete-Qwen-2.5-3b-CoT-RP.Q3_K_S.gguf	Q3_K_S	1.48GB
Replete-Qwen-2.5-3b-CoT-RP.IQ3_M.gguf	IQ3_M	1.51GB
Replete-Qwen-2.5-3b-CoT-RP.Q3_K.gguf	Q3_K	1.61GB
Replete-Qwen-2.5-3b-CoT-RP.Q3_K_M.gguf	Q3_K_M	1.61GB
Replete-Qwen-2.5-3b-CoT-RP.Q3_K_L.gguf	Q3_K_L	1.71GB
Replete-Qwen-2.5-3b-CoT-RP.IQ4_XS.gguf	IQ4_XS	1.79GB
Replete-Qwen-2.5-3b-CoT-RP.Q4_0.gguf	Q4_0	1.86GB
Replete-Qwen-2.5-3b-CoT-RP.IQ4_NL.gguf	IQ4_NL	1.87GB
Replete-Qwen-2.5-3b-CoT-RP.Q4_K_S.gguf	Q4_K_S	1.87GB
Replete-Qwen-2.5-3b-CoT-RP.Q4_K.gguf	Q4_K	1.96GB
Replete-Qwen-2.5-3b-CoT-RP.Q4_K_M.gguf	Q4_K_M	1.96GB
Replete-Qwen-2.5-3b-CoT-RP.Q4_1.gguf	Q4_1	2.04GB
Replete-Qwen-2.5-3b-CoT-RP.Q5_0.gguf	Q5_0	2.22GB
Replete-Qwen-2.5-3b-CoT-RP.Q5_K_S.gguf	Q5_K_S	2.22GB
Replete-Qwen-2.5-3b-CoT-RP.Q5_K.gguf	Q5_K	2.27GB
Replete-Qwen-2.5-3b-CoT-RP.Q5_K_M.gguf	Q5_K_M	2.27GB
Replete-Qwen-2.5-3b-CoT-RP.Q5_1.gguf	Q5_1	2.4GB
Replete-Qwen-2.5-3b-CoT-RP.Q6_K.gguf	Q6_K	2.6GB
Replete-Qwen-2.5-3b-CoT-RP.Q8_0.gguf	Q8_0	3.37GB

Original model description:

base_model:

• bunnycore/Qwen-2.5-3b-RP
• Replete-AI/Replete-LLM-V2.5-Qwen-3b
• bunnycore/Qwen-2.5-3b-rp-mix-lora
• bunnycore/Qwen-2.5-3b-RP
• bunnycore/Qwen-2.5-3b-rp-mix-lora library_name: transformers tags:
• mergekit
• merge

---

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using bunnycore/Qwen-2.5-3b-RP as a base.

Models Merged

The following models were included in the merge:

• Replete-AI/Replete-LLM-V2.5-Qwen-3b + bunnycore/Qwen-2.5-3b-rp-mix-lora
• bunnycore/Qwen-2.5-3b-RP + bunnycore/Qwen-2.5-3b-rp-mix-lora

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: bunnycore/Qwen-2.5-3b-RP+bunnycore/Qwen-2.5-3b-rp-mix-lora
    parameters:
      density: 0.5
      weight: 0.5
  - model: Replete-AI/Replete-LLM-V2.5-Qwen-3b+bunnycore/Qwen-2.5-3b-rp-mix-lora
    parameters:
      density: 0.5
      weight: 0.5

merge_method: dare_ties
base_model: bunnycore/Qwen-2.5-3b-RP
parameters:
  normalize: false
  int8_mask: true
dtype: float16

Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more quants, at much higher speed, than I would otherwise be able to.