--- base_model: tiiuae/falcon-180B datasets: - tiiuae/falcon-refinedweb extra_gated_button_content: I agree to the terms and conditions of the Falcon-180B TII license and to the acceptable use policy extra_gated_heading: Acknowledge license to access the repository extra_gated_prompt: You agree to the [Falcon-180B TII license](https://huggingface.co/spaces/tiiuae/falcon-180b-license/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/tiiuae/falcon-180b-license/blob/main/ACCEPTABLE_USE_POLICY.txt). language: - en - de - es - fr library_name: transformers license: unknown quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/tiiuae/falcon-180B <!-- provided-files --> ## 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/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ1_S.gguf) | i1-IQ1_S | 38.4 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ1_M.gguf) | i1-IQ1_M | 42.0 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 47.9 | | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ2_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ2_XS.gguf.part2of2) | i1-IQ2_XS | 53.1 | | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ2_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ2_S.gguf.part2of2) | i1-IQ2_S | 56.6 | | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ2_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ2_M.gguf.part2of2) | i1-IQ2_M | 61.3 | | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q2_K.gguf.part2of2) | i1-Q2_K | 66.9 | IQ3_XXS probably better | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ3_XXS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ3_XXS.gguf.part2of2) | i1-IQ3_XXS | 69.5 | lower quality | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ3_XS.gguf.part2of2) | i1-IQ3_XS | 75.4 | | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ3_S.gguf.part2of2) | i1-IQ3_S | 77.9 | beats Q3_K* | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q3_K_S.gguf.part2of2) | i1-Q3_K_S | 77.9 | IQ3_XS probably better | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 81.5 | | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 85.6 | IQ3_S probably better | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 92.1 | IQ3_M probably better | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 96.0 | | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q4_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q4_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q4_K_S.gguf.part3of3) | i1-Q4_K_S | 101.6 | optimal size/speed/quality | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q4_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q4_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q4_0.gguf.part3of3) | i1-Q4_0 | 102.1 | fast, low quality | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q4_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q4_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q4_K_M.gguf.part3of3) | i1-Q4_K_M | 108.9 | fast, recommended | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q5_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q5_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q5_K_S.gguf.part3of3) | i1-Q5_K_S | 123.9 | | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q5_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q5_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q5_K_M.gguf.part3of3) | i1-Q5_K_M | 131.1 | | | [PART 1](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/falcon-180B-i1-GGUF/resolve/main/falcon-180B.i1-Q6_K.gguf.part3of3) | i1-Q6_K | 147.6 | 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. 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. <!-- end -->