--- exported_from: NobodyExistsOnTheInternet/clown-SUV-4x70b language: - en library_name: transformers license: mit quantized_by: mradermacher --- ## About weighted/imatrix quants of https://huggingface.co/NobodyExistsOnTheInternet/clown-SUV-4x70b static quants are available at https://huggingface.co/mradermacher/clown-SUV-4x70b-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 | |:-----|:-----|--------:|:------| | [PART 1](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q2_K.gguf.part2of2) | i1-Q2_K | 87.1 | IQ3_XXS probably better | | [PART 1](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q3_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q3_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q3_K_S.gguf.part3of3) | i1-Q3_K_S | 103.0 | IQ3_XS probably better | | [PART 1](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q3_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q3_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q3_K_M.gguf.part3of3) | i1-Q3_K_M | 114.3 | IQ3_S probably better | | [PART 1](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q3_K_L.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q3_K_L.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q3_K_L.gguf.part3of3) | i1-Q3_K_L | 123.8 | IQ3_M probably better | | [PART 1](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-IQ4_XS.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-IQ4_XS.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-IQ4_XS.gguf.part3of3) | i1-IQ4_XS | 127.1 | | | [PART 1](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q4_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q4_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q4_0.gguf.part3of3) | i1-Q4_0 | 135.0 | | | [PART 1](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q4_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q4_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q4_K_S.gguf.part3of3) | i1-Q4_K_S | 135.7 | optimal size/speed/quality | | [PART 1](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q4_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q4_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q4_K_M.gguf.part3of3) | i1-Q4_K_M | 144.2 | fast, recommended | | [PART 1](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q5_K_S.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q5_K_S.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q5_K_S.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q5_K_S.gguf.part4of4) | i1-Q5_K_S | 164.1 | | | [PART 1](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q5_K_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q5_K_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q5_K_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q5_K_M.gguf.part4of4) | i1-Q5_K_M | 169.2 | | | [P1](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q6_K.gguf.part1of5) [P2](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q6_K.gguf.part2of5) [P3](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q6_K.gguf.part3of5) [P4](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q6_K.gguf.part4of5) [P5](https://huggingface.co/mradermacher/clown-SUV-4x70b-i1-GGUF/resolve/main/clown-SUV-4x70b.i1-Q6_K.gguf.part5of5) | i1-Q6_K | 195.7 | 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 ## 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.