--- base_model: - CultriX/MonaTrix-v4 - mlabonne/OmniTruthyBeagle-7B-v0 - CultriX/MoNeuTrix-7B-v1 - paulml/OmniBeagleSquaredMBX-v3-7B exported_from: CultriX/NeuralMona_MoE-4x7B language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - moe - frankenmoe - merge - mergekit - lazymergekit - CultriX/MonaTrix-v4 - mlabonne/OmniTruthyBeagle-7B-v0 - CultriX/MoNeuTrix-7B-v1 - paulml/OmniBeagleSquaredMBX-v3-7B --- ## About weighted/imatrix quants of https://huggingface.co/CultriX/NeuralMona_MoE-4x7B static quants are available at https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-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 | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-IQ1_S.gguf) | i1-IQ1_S | 5.3 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-IQ1_M.gguf) | i1-IQ1_M | 5.8 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.7 | | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.4 | | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-IQ2_S.gguf) | i1-IQ2_S | 7.6 | | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-IQ2_M.gguf) | i1-IQ2_M | 8.3 | | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-Q2_K.gguf) | i1-Q2_K | 9.1 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.6 | lower quality | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.1 | | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 10.7 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-IQ3_S.gguf) | i1-IQ3_S | 10.7 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-IQ3_M.gguf) | i1-IQ3_M | 10.9 | | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.8 | IQ3_S probably better | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.8 | IQ3_M probably better | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 13.1 | | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 13.9 | slightly worse than Q4_K_S | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-Q4_0.gguf) | i1-Q4_0 | 13.9 | fast, low quality | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.0 | optimal size/speed/quality | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.9 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.9 | | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.4 | | | [GGUF](https://huggingface.co/mradermacher/NeuralMona_MoE-4x7B-i1-GGUF/resolve/main/NeuralMona_MoE-4x7B.i1-Q6_K.gguf) | i1-Q6_K | 20.1 | 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 ## 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.