--- base_model: ibivibiv/giant-hydra-moe-240b language: - en library_name: transformers license: llama2 quantized_by: mradermacher tags: - moe - moerge --- ## About static quants of https://huggingface.co/ibivibiv/giant-hydra-moe-240b weighted/imatrix quants are available at https://huggingface.co/mradermacher/giant-hydra-moe-240b-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/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q2_K.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q2_K.gguf.split-ab) | Q2_K | 87.6 | | | [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q3_K_XS.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q3_K_XS.gguf.split-ab) | Q3_K_XS | 96.5 | | | [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q3_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q3_K_S.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q3_K_S.gguf.split-ac) | Q3_K_S | 103.5 | | | [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q3_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q3_K_M.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q3_K_M.gguf.split-ac) | Q3_K_M | 114.8 | lower quality | | [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q3_K_L.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q3_K_L.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q3_K_L.gguf.split-ac) | Q3_K_L | 124.3 | | | [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q4_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q4_K_S.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q4_K_S.gguf.split-ac) | Q4_K_S | 136.2 | fast, recommended | | [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q4_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q4_K_M.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q4_K_M.gguf.split-ac) | Q4_K_M | 144.8 | fast, recommended | | [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q5_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q5_K_S.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q5_K_S.gguf.split-ac) [PART 4](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q5_K_S.gguf.split-ad) | Q5_K_S | 164.7 | | | [PART 1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q5_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q5_K_M.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q5_K_M.gguf.split-ac) [PART 4](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q5_K_M.gguf.split-ad) | Q5_K_M | 169.7 | | | [P1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q6_K.gguf.split-aa) [P2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q6_K.gguf.split-ab) [P3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q6_K.gguf.split-ac) [P4](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q6_K.gguf.split-ad) [P5](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q6_K.gguf.split-ae) | Q6_K | 196.3 | very good quality | | [P1](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q8_0.gguf.split-aa) [P2](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q8_0.gguf.split-ab) [P3](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q8_0.gguf.split-ac) [P4](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q8_0.gguf.split-ad) [P5](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q8_0.gguf.split-ae) [P6](https://huggingface.co/mradermacher/giant-hydra-moe-240b-GGUF/resolve/main/giant-hydra-moe-240b.Q8_0.gguf.split-af) | Q8_0 | 253.9 | 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.