├── .gitignore ├── LICENSE ├── README.md ├── benchmarks.md ├── commands.md ├── i-quants.md ├── images ├── block-quantization.png ├── codebook.png ├── imatrix-code.png ├── imatrix-objective.png ├── importance-matrix.png ├── names.png ├── no-papers.png ├── size-diff.png ├── super-blocks.png ├── type0.png ├── type1.png └── vector-quantization.png ├── importance-matrix.md ├── k-quants.md ├── legacy-quants.md └── naming.md /.gitignore: -------------------------------------------------------------------------------- 1 | .claude -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/README.md -------------------------------------------------------------------------------- /benchmarks.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/benchmarks.md -------------------------------------------------------------------------------- /commands.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/commands.md -------------------------------------------------------------------------------- /i-quants.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/i-quants.md -------------------------------------------------------------------------------- /images/block-quantization.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/images/block-quantization.png -------------------------------------------------------------------------------- /images/codebook.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/images/codebook.png -------------------------------------------------------------------------------- /images/imatrix-code.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/images/imatrix-code.png -------------------------------------------------------------------------------- /images/imatrix-objective.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/images/imatrix-objective.png -------------------------------------------------------------------------------- /images/importance-matrix.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/images/importance-matrix.png -------------------------------------------------------------------------------- /images/names.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/images/names.png -------------------------------------------------------------------------------- /images/no-papers.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/images/no-papers.png -------------------------------------------------------------------------------- /images/size-diff.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/images/size-diff.png -------------------------------------------------------------------------------- /images/super-blocks.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/images/super-blocks.png -------------------------------------------------------------------------------- /images/type0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/images/type0.png -------------------------------------------------------------------------------- /images/type1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/images/type1.png -------------------------------------------------------------------------------- /images/vector-quantization.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/images/vector-quantization.png -------------------------------------------------------------------------------- /importance-matrix.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/importance-matrix.md -------------------------------------------------------------------------------- /k-quants.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/k-quants.md -------------------------------------------------------------------------------- /legacy-quants.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/legacy-quants.md -------------------------------------------------------------------------------- /naming.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iuliaturc/gguf-docs/HEAD/naming.md --------------------------------------------------------------------------------