--- base_model: wolfram/miqu-1-120b language: - en - de - fr - es - it library_name: transformers license: other quantized_by: mradermacher tags: - mergekit - merge --- ## About weighted/imatrix quants of https://huggingface.co/wolfram/miqu-1-120b static quants are available at https://huggingface.co/mradermacher/miqu-1-120b-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-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-IQ1_S.gguf) | i1-IQ1_S | 25.7 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 32.2 | | | [GGUF](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 35.8 | | | [GGUF](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-IQ2_S.gguf) | i1-IQ2_S | 37.6 | | | [GGUF](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-IQ2_M.gguf) | i1-IQ2_M | 40.9 | | | [GGUF](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q2_K.gguf) | i1-Q2_K | 44.6 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 46.6 | lower quality | | [GGUF](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 49.4 | | | [PART 1](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q3_K_S.gguf.part2of2) | i1-Q3_K_S | 52.2 | IQ3_XS probably better | | [PART 1](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-IQ3_S.gguf.part2of2) | i1-IQ3_S | 52.4 | beats Q3_K* | | [PART 1](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 54.2 | | | [PART 1](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 58.2 | IQ3_S probably better | | [PART 1](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 63.4 | IQ3_M probably better | | [PART 1](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 68.7 | optimal size/speed/quality | | [PART 1](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 72.6 | fast, recommended | | [PART 1](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 83.2 | | | [PART 1](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 85.4 | | | [PART 1](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/miqu-1-120b-i1-GGUF/resolve/main/miqu-1-120b.i1-Q6_K.gguf.part3of3) | i1-Q6_K | 99.1 | practically like static Q6_K | 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.