GGUF Quantised Models for Qwen2.5_14B_Instruct_Johnny_Silverhand_Merged

This repository contains GGUF format model files for lewiswatson/Qwen2.5_14B_Instruct_Johnny_Silverhand_Merged-GGUF, quantised.

Original Model

The original fine-tuned model used to generate these quantisations can be found here: lewiswatson/Qwen2.5_14B_Instruct_Johnny_Silverhand_Merged-GGUF

File	Size
`Qwen2.5-14B-Instruct_Johnny_Silverhand_Merged.IQ4_XS.gguf`	7.62 GB
`Qwen2.5-14B-Instruct_Johnny_Silverhand_Merged.Q2_K.gguf`	5.37 GB
`Qwen2.5-14B-Instruct_Johnny_Silverhand_Merged.Q3_K_L.gguf`	7.38 GB
`Qwen2.5-14B-Instruct_Johnny_Silverhand_Merged.Q3_K_M.gguf`	6.84 GB
`Qwen2.5-14B-Instruct_Johnny_Silverhand_Merged.Q3_K_S.gguf`	6.20 GB
`Qwen2.5-14B-Instruct_Johnny_Silverhand_Merged.Q4_K_M.gguf`	8.37 GB
`Qwen2.5-14B-Instruct_Johnny_Silverhand_Merged.Q4_K_S.gguf`	7.98 GB
`Qwen2.5-14B-Instruct_Johnny_Silverhand_Merged.Q5_K_M.gguf`	9.79 GB
`Qwen2.5-14B-Instruct_Johnny_Silverhand_Merged.Q5_K_S.gguf`	9.56 GB
`Qwen2.5-14B-Instruct_Johnny_Silverhand_Merged.Q6_K.gguf`	11.29 GB
`Qwen2.5-14B-Instruct_Johnny_Silverhand_Merged.Q8_0.gguf`	14.62 GB
`Qwen2.5-14B-Instruct_Johnny_Silverhand_Merged.f16.gguf`	27.52 GB

This repository was automatically created using a script on 2025-04-15.

GGUF

Model size

15B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Unable to build the model tree, the base model loops to the model itself. Learn more.