--- language: - en library_name: transformers quantized_by: mradermacher source_fix: convert --vocab-type bpe --pad-vocab --- ## About weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## 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/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q2_K.gguf.part2of2) | Q2_K | 51.6 | | | [PART 1](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.IQ3_S.gguf.part2of2) | IQ3_S | 59.6 | beats Q3_K* | | [PART 1](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q3_K_S.gguf.part2of2) | Q3_K_S | 59.6 | | | [PART 1](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q3_K_M.gguf.part2of2) | Q3_K_M | 66.3 | lower quality | | [PART 1](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q3_K_L.gguf.part2of2) | Q3_K_L | 72.1 | | | [PART 1](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q4_0.gguf.part2of2) | Q4_0 | 76.5 | | | [PART 1](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q4_K_S.gguf.part2of2) | Q4_K_S | 77.0 | fast, recommended | | [PART 1](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q4_K_M.gguf.part2of2) | Q4_K_M | 81.4 | fast, recommended | | [PART 1](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q5_K_S.gguf.part2of2) | Q5_K_S | 92.3 | | | [PART 1](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q5_K_M.gguf.part2of2) | Q5_K_M | 94.9 | | | [PART 1](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q6_K.gguf.part3of3) | Q6_K | 109.2 | very good quality | | [PART 1](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.Q8_0.gguf.part3of3) | Q8_0 | 139.9 | fast, best quality | | [P1](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.SOURCE.gguf.part01of11) [P2](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.SOURCE.gguf.part02of11) [P3](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.SOURCE.gguf.part03of11) [P4](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.SOURCE.gguf.part04of11) [P5](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.SOURCE.gguf.part05of11) [P6](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.SOURCE.gguf.part06of11) [P7](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.SOURCE.gguf.part07of11) [P8](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.SOURCE.gguf.part08of11) [P9](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.SOURCE.gguf.part09of11) [P10](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.SOURCE.gguf.part10of11) [P11](https://huggingface.co/mradermacher/Blitz-AI-ULTRA-GGUF/resolve/main/Blitz-AI-ULTRA.SOURCE.gguf.part11of11) | SOURCE | 512.6 | 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 ## 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.