aitorrent/dolphin-2.9.3-qwen2-0.5b-GGUF-torrent

aitorrent/dolphin-2.9.3-qwen2-0.5b-GGUF-torrent
Photo by TJ Fitzsimmons / Unsplash

About

This repository provides static quants for the dolphin-2.9.3-qwen2-0.5b model, originally from https://huggingface.co/cognitivecomputations/dolphin-2.9.3-qwen2-0.5b. Additionally, weighted/imatrix quants are available at https://huggingface.co/mradermacher/dolphin-2.9.3-qwen2-0.5b-i1-GGUF.

Usage

For guidance on using GGUF files, please refer to TheBloke's READMEs, which include instructions on concatenating multi-part files.

Provided Quants

The following quants are available, sorted by size (not necessarily quality). IQ-quants are often preferred over similar-sized non-IQ quants.

Link Type Size/GB Notes
GGUF Q3_K_S 0.4
GGUF IQ3_S 0.4 Beats Q3_K*
GGUF IQ3_XS 0.4
GGUF Q2_K 0.4
GGUF IQ3_M 0.4
GGUF IQ4_XS 0.5
GGUF Q3_K_M 0.5 Lower quality
GGUF Q3_K_L 0.5
GGUF Q4_K_S 0.5 Fast, recommended
GGUF Q4_K_M 0.5 Fast, recommended
GGUF Q5_K_S 0.5
GGUF Q5_K_M 0.5
GGUF Q6_K 0.6 Very good quality
GGUF Q8_0 0.6 Fast, best quality
GGUF f16 1.1 16 bpw, overkill

Comparison Graph

ikawrakow's graph compares some lower-quality quant types (lower is better):

[image.png]

Additional Insights

Artefact2's thoughts on the matter can be found here: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

Credit: Original description from https://huggingface.co/cognitivecomputations/dolphin-2.9.3-qwen2-0.5b.