--- exported_from: GritLM/GritLM-8x7B-KTO language: - en library_name: transformers quantized_by: mradermacher --- ## About weighted/imatrix quants of https://huggingface.co/GritLM/GritLM-8x7B-KTO static quants are available at https://huggingface.co/mradermacher/GritLM-8x7B-KTO-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/GritLM-8x7B-KTO-i1-GGUF/resolve/main/GritLM-8x7B-KTO.i1-Q2_K.gguf) | i1-Q2_K | 17.4 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/GritLM-8x7B-KTO-i1-GGUF/resolve/main/GritLM-8x7B-KTO.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.3 | lower quality | | [GGUF](https://huggingface.co/mradermacher/GritLM-8x7B-KTO-i1-GGUF/resolve/main/GritLM-8x7B-KTO.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.6 | IQ3_S probably better | | [GGUF](https://huggingface.co/mradermacher/GritLM-8x7B-KTO-i1-GGUF/resolve/main/GritLM-8x7B-KTO.i1-Q4_K_S.gguf) | i1-Q4_K_S | 26.8 | optimal size/speed/quality | | [GGUF](https://huggingface.co/mradermacher/GritLM-8x7B-KTO-i1-GGUF/resolve/main/GritLM-8x7B-KTO.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.5 | fast, recommended | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.