--- base_model: athirdpath/Harmonia-20B exported_from: athirdpath/Harmonia-no_robots-20b language: - en library_name: transformers license: cc-by-nc-4.0 quantized_by: mradermacher tags: - generated_from_trainer --- ## About static quants of https://huggingface.co/athirdpath/Harmonia-no_robots-20b weighted/imatrix quants are available at https://huggingface.co/mradermacher/Harmonia-no_robots-20b-i1-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/Harmonia-no_robots-20b-GGUF/resolve/main/Harmonia-no_robots-20b.Q2_K.gguf) | Q2_K | 7.7 | | | [GGUF](https://huggingface.co/mradermacher/Harmonia-no_robots-20b-GGUF/resolve/main/Harmonia-no_robots-20b.IQ3_XS.gguf) | IQ3_XS | 8.5 | | | [GGUF](https://huggingface.co/mradermacher/Harmonia-no_robots-20b-GGUF/resolve/main/Harmonia-no_robots-20b.IQ3_S.gguf) | IQ3_S | 9.0 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Harmonia-no_robots-20b-GGUF/resolve/main/Harmonia-no_robots-20b.Q3_K_S.gguf) | Q3_K_S | 9.0 | | | [GGUF](https://huggingface.co/mradermacher/Harmonia-no_robots-20b-GGUF/resolve/main/Harmonia-no_robots-20b.IQ3_M.gguf) | IQ3_M | 9.4 | | | [GGUF](https://huggingface.co/mradermacher/Harmonia-no_robots-20b-GGUF/resolve/main/Harmonia-no_robots-20b.Q3_K_M.gguf) | Q3_K_M | 10.0 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Harmonia-no_robots-20b-GGUF/resolve/main/Harmonia-no_robots-20b.Q3_K_L.gguf) | Q3_K_L | 10.9 | | | [GGUF](https://huggingface.co/mradermacher/Harmonia-no_robots-20b-GGUF/resolve/main/Harmonia-no_robots-20b.IQ4_XS.gguf) | IQ4_XS | 11.0 | | | [GGUF](https://huggingface.co/mradermacher/Harmonia-no_robots-20b-GGUF/resolve/main/Harmonia-no_robots-20b.Q4_K_S.gguf) | Q4_K_S | 11.7 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Harmonia-no_robots-20b-GGUF/resolve/main/Harmonia-no_robots-20b.Q4_K_M.gguf) | Q4_K_M | 12.3 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Harmonia-no_robots-20b-GGUF/resolve/main/Harmonia-no_robots-20b.Q5_K_S.gguf) | Q5_K_S | 14.1 | | | [GGUF](https://huggingface.co/mradermacher/Harmonia-no_robots-20b-GGUF/resolve/main/Harmonia-no_robots-20b.Q5_K_M.gguf) | Q5_K_M | 14.5 | | | [GGUF](https://huggingface.co/mradermacher/Harmonia-no_robots-20b-GGUF/resolve/main/Harmonia-no_robots-20b.Q6_K.gguf) | Q6_K | 16.7 | very good quality | | [GGUF](https://huggingface.co/mradermacher/Harmonia-no_robots-20b-GGUF/resolve/main/Harmonia-no_robots-20b.Q8_0.gguf) | Q8_0 | 21.5 | fast, best quality | 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.