--- base_model: xai-org/grok-2 language: - en library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## About static quants of https://huggingface.co/xai-org/grok-2 ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#grok-2-GGUF).*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/grok-2-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/grok-2-GGUF/resolve/main/grok-2.Q2_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q2_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q2_K.gguf.part3of3) | Q2_K | 100.2 | | | [PART 1](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q3_K_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q3_K_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q3_K_S.gguf.part3of3) | Q3_K_S | 118.1 | | | [PART 1](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q3_K_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q3_K_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q3_K_M.gguf.part3of3) | Q3_K_M | 130.2 | lower quality | | [PART 1](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q3_K_L.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q3_K_L.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q3_K_L.gguf.part3of3) | Q3_K_L | 139.2 | | | [PART 1](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.IQ4_XS.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.IQ4_XS.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.IQ4_XS.gguf.part3of3) | IQ4_XS | 146.5 | | | [PART 1](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q4_K_S.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q4_K_S.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q4_K_S.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q4_K_S.gguf.part4of4) | Q4_K_S | 154.4 | fast, recommended | | [PART 1](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q4_K_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q4_K_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q4_K_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q4_K_M.gguf.part4of4) | Q4_K_M | 164.2 | fast, recommended | | [PART 1](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q5_K_S.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q5_K_S.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q5_K_S.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q5_K_S.gguf.part4of4) | Q5_K_S | 186.0 | | | [PART 1](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q5_K_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q5_K_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q5_K_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q5_K_M.gguf.part4of4) | Q5_K_M | 191.7 | | | [P1](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q6_K.gguf.part1of5) [P2](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q6_K.gguf.part2of5) [P3](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q6_K.gguf.part3of5) [P4](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q6_K.gguf.part4of5) [P5](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q6_K.gguf.part5of5) | Q6_K | 221.5 | very good quality | | [P1](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q8_0.gguf.part1of6) [P2](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q8_0.gguf.part2of6) [P3](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q8_0.gguf.part3of6) [P4](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q8_0.gguf.part4of6) [P5](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q8_0.gguf.part5of6) [P6](https://huggingface.co/mradermacher/grok-2-GGUF/resolve/main/grok-2.Q8_0.gguf.part6of6) | Q8_0 | 286.5 | fast, best quality | 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.