--- base_model: miqudev/miqu-1-70b language: - en library_name: transformers quantized_by: mradermacher --- ## About weighted/imatrix quants of https://huggingface.co/miqudev/miqu-1-70b static quants are available at https://huggingface.co/mradermacher/miqu-1-70b-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/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-IQ1_S.gguf) | i1-IQ1_S | 14.6 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-IQ1_M.gguf) | i1-IQ1_M | 16.0 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.4 | | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.4 | | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-IQ2_S.gguf) | i1-IQ2_S | 21.5 | | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-IQ2_M.gguf) | i1-IQ2_M | 23.3 | | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 23.7 | very low quality | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 26.7 | lower quality | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.4 | | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-IQ3_S.gguf) | i1-IQ3_S | 30.0 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.0 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-IQ3_M.gguf) | i1-IQ3_M | 31.0 | | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.2 | IQ3_M probably better | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 36.9 | | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 39.0 | fast on arm, low quality | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 39.0 | fast on arm+i8mm, low quality | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 39.0 | fast on arm+sve, low quality | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 39.1 | prefer IQ4_XS | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q4_0.gguf) | i1-Q4_0 | 39.1 | fast, low quality | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.3 | optimal size/speed/quality | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.5 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q4_1.gguf) | i1-Q4_1 | 43.3 | | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 47.6 | | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q5_0.gguf) | i1-Q5_0 | 47.7 | | | [GGUF](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 48.9 | | | [PART 1](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q5_1.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-70b-i1-GGUF/resolve/main/miqu-1-70b.i1-Q5_1.gguf.part2of2) | i1-Q5_1 | 51.9 | | 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 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.