--- base_model: quantumaikr/falcon-180B-WizardLM_Orca datasets: - tiiuae/falcon-refinedweb - pankajmathur/WizardLM_Orca language: - en - de - es - fr library_name: transformers quantized_by: mradermacher --- ## About static quants of https://huggingface.co./quantumaikr/falcon-180B-WizardLM_Orca weighted/imatrix quants are available at https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-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 | |:-----|:-----|--------:|:------| | [PART 1](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q2_K.gguf.part1of2) [PART 2](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q2_K.gguf.part2of2) | Q2_K | 65.9 | | | [PART 1](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.IQ3_XS.gguf.part2of2) | IQ3_XS | 74.4 | | | [PART 1](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.IQ3_S.gguf.part2of2) | IQ3_S | 76.8 | beats Q3_K* | | [PART 1](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q3_K_S.gguf.part2of2) | Q3_K_S | 76.8 | | | [PART 1](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.IQ3_M.gguf.part2of2) | IQ3_M | 80.5 | | | [PART 1](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q3_K_M.gguf.part2of2) | Q3_K_M | 84.6 | lower quality | | [PART 1](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q3_K_L.gguf.part2of2) | Q3_K_L | 91.1 | | | [PART 1](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.IQ4_XS.gguf.part2of2) | IQ4_XS | 96.4 | | | [PART 1](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q4_K_S.gguf.part1of3) [PART 2](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q4_K_S.gguf.part2of3) [PART 3](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q4_K_S.gguf.part3of3) | Q4_K_S | 100.6 | fast, recommended | | [PART 1](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q4_K_M.gguf.part1of3) [PART 2](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q4_K_M.gguf.part2of3) [PART 3](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q4_K_M.gguf.part3of3) | Q4_K_M | 107.9 | fast, recommended | | [PART 1](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q5_K_S.gguf.part1of3) [PART 2](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q5_K_S.gguf.part2of3) [PART 3](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q5_K_S.gguf.part3of3) | Q5_K_S | 122.9 | | | [PART 1](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q5_K_M.gguf.part1of3) [PART 2](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q5_K_M.gguf.part2of3) [PART 3](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q5_K_M.gguf.part3of3) | Q5_K_M | 130.1 | | | [PART 1](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q6_K.gguf.part1of4) [PART 2](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q6_K.gguf.part2of4) [PART 3](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q6_K.gguf.part3of4) [PART 4](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q6_K.gguf.part4of4) | Q6_K | 146.6 | very good quality | | [PART 1](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q8_0.gguf.part1of4) [PART 2](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q8_0.gguf.part2of4) [PART 3](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q8_0.gguf.part3of4) [PART 4](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.Q8_0.gguf.part4of4) | Q8_0 | 189.8 | fast, best quality | | [P1](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.SOURCE.gguf.part1of8) [P2](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.SOURCE.gguf.part2of8) [P3](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.SOURCE.gguf.part3of8) [P4](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.SOURCE.gguf.part4of8) [P5](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.SOURCE.gguf.part5of8) [P6](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.SOURCE.gguf.part6of8) [P7](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.SOURCE.gguf.part7of8) [P8](https://huggingface.co./mradermacher/falcon-180B-WizardLM_Orca-GGUF/resolve/main/falcon-180B-WizardLM_Orca.SOURCE.gguf.part8of8) | SOURCE | 357.2 | source gguf, only provided when it was hard to come by | 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.