|
996 | 996 | - filename: llama-cpp/mmproj/Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-MTP-Q4_K_M/mmproj-F32.gguf |
997 | 997 | sha256: fdc443e974cad1f61c45af1cfd5580855855ddce0d6c14cc500a5714c486ac1d |
998 | 998 | uri: https://huggingface.co/DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF/resolve/main/mmproj-F32.gguf |
| 999 | +- &qwopus3-6-27b-fusion |
| 1000 | + name: "qwopus3.6-27b-fusion" |
| 1001 | + variants: |
| 1002 | + - model: qwopus3.6-27b-fusion-q8 |
| 1003 | + url: "github:mudler/LocalAI/gallery/virtual.yaml@master" |
| 1004 | + urls: |
| 1005 | + - https://huggingface.co/Qwen/Qwen3.6-27B |
| 1006 | + - https://huggingface.co/KyleHessling1/Qwopus3.6-27B-Fusion-GGUF |
| 1007 | + description: | |
| 1008 | + Qwopus3.6-27B Fusion is an experimental 27B Qwen3.6 merge that combines the |
| 1009 | + Qwopus reasoning and coding fine-tunes. It targets agentic coding and |
| 1010 | + general reasoning, supports the Qwen3.6 262K context window, and retains |
| 1011 | + the base model's MTP head. This default entry uses the 16.8 GB Q4_K_M GGUF. |
| 1012 | + license: qwen |
| 1013 | + tags: |
| 1014 | + - llm |
| 1015 | + - gguf |
| 1016 | + - reasoning |
| 1017 | + - thinking |
| 1018 | + - mtp |
| 1019 | + overrides: |
| 1020 | + backend: llama-cpp |
| 1021 | + function: |
| 1022 | + automatic_tool_parsing_fallback: true |
| 1023 | + grammar: |
| 1024 | + disable: true |
| 1025 | + known_usecases: |
| 1026 | + - chat |
| 1027 | + options: |
| 1028 | + - use_jinja:true |
| 1029 | + - spec_type:draft-mtp |
| 1030 | + - spec_n_max:6 |
| 1031 | + - spec_p_min:0.75 |
| 1032 | + parameters: |
| 1033 | + model: llama-cpp/models/Qwopus3.6-27B-Fusion-Q4_K_M/Qwopus3.6-27B-Fusion-Q4_K_M.gguf |
| 1034 | + template: |
| 1035 | + use_tokenizer_template: true |
| 1036 | + files: |
| 1037 | + - filename: llama-cpp/models/Qwopus3.6-27B-Fusion-Q4_K_M/Qwopus3.6-27B-Fusion-Q4_K_M.gguf |
| 1038 | + sha256: 6d4e6e9ffba84ffe5166969303d4918f3a31682d75862416827412cee8f20d5d |
| 1039 | + uri: huggingface://KyleHessling1/Qwopus3.6-27B-Fusion-GGUF/Qwopus3.6-27B-Fusion-Q4_K_M.gguf |
| 1040 | +- !!merge <<: *qwopus3-6-27b-fusion |
| 1041 | + name: "qwopus3.6-27b-fusion-q8" |
| 1042 | + variants: null |
| 1043 | + description: | |
| 1044 | + Qwopus3.6-27B Fusion in the higher-fidelity 29.0 GB Q8_0 GGUF format. |
| 1045 | + It retains the base model's MTP head for speculative decoding. |
| 1046 | + overrides: |
| 1047 | + backend: llama-cpp |
| 1048 | + function: |
| 1049 | + automatic_tool_parsing_fallback: true |
| 1050 | + grammar: |
| 1051 | + disable: true |
| 1052 | + known_usecases: |
| 1053 | + - chat |
| 1054 | + options: |
| 1055 | + - use_jinja:true |
| 1056 | + - spec_type:draft-mtp |
| 1057 | + - spec_n_max:6 |
| 1058 | + - spec_p_min:0.75 |
| 1059 | + parameters: |
| 1060 | + model: llama-cpp/models/Qwopus3.6-27B-Fusion-Q8_0/Qwopus3.6-27B-Fusion-Q8_0.gguf |
| 1061 | + template: |
| 1062 | + use_tokenizer_template: true |
| 1063 | + files: |
| 1064 | + - filename: llama-cpp/models/Qwopus3.6-27B-Fusion-Q8_0/Qwopus3.6-27B-Fusion-Q8_0.gguf |
| 1065 | + sha256: 5594e1776b75beedf4a54b933bba386dc83a0883417e3bcd9ef53fdfd120d5b6 |
| 1066 | + uri: huggingface://KyleHessling1/Qwopus3.6-27B-Fusion-GGUF/Qwopus3.6-27B-Fusion-Q8_0.gguf |
999 | 1067 | - name: "minicpm5-1b-claude-opus-fable5-v2-thinking" |
1000 | 1068 | url: "github:mudler/LocalAI/gallery/virtual.yaml@master" |
1001 | 1069 | urls: |
|
0 commit comments