From 9bceeb1e5dc85befc4a6f6a5c58147eb3d4ce101 Mon Sep 17 00:00:00 2001 From: localai-org-maint-bot Date: Sat, 17 Oct 2026 00:54:45 +0200 Subject: [PATCH] feat(gallery): add MiniCPM-V 4.7 1B variants (#12684) Add official Q4, Q5, Q6, and Q8 GGUF builds with the F16 vision projector. Group them for automatic selection and document installation. Pin downloads to one Hugging Face revision with verified SHA256 values. Assisted-by: Codex:gpt-6 Signed-off-by: Ettore Di Giacinto Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> --- docs/content/features/model-gallery.md | 17 +++ gallery/index.yaml | 144 +++++++++++++++++++++++++ 2 files changed, 161 insertions(+) diff --git a/docs/content/features/model-gallery.md b/docs/content/features/model-gallery.md index f650118b0..c430a6a71 100644 --- a/docs/content/features/model-gallery.md +++ b/docs/content/features/model-gallery.md @@ -44,6 +44,23 @@ Both views store the view, search, filter, and selection in the URL. Installing from Explore does not move you away from the catalog; the entry updates in place when the operation finishes. +### MiniCPM-V 4.7 1B + +[MiniCPM-V 4.7 1B](https://huggingface.co/openbmb/MiniCPM-V-4.7-1B) +supports text chat and image understanding through the llama.cpp backend. +The gallery includes official Q4_K_M, Q5_K_M, Q6_K, and Q8_0 GGUF builds. +Each build includes the F16 vision projector and uses an 8,192-token default context. + +Install the family with automatic variant selection: + +```bash +local-ai models install minicpm-v-4_7-1b-q4 +``` + +Select a specific build with `--variant minicpm-v-4_7-1b-q4`, +`--variant minicpm-v-4_7-1b-q5`, `--variant minicpm-v-4_7-1b-q6`, +or `--variant minicpm-v-4_7-1b-q8`. + ### Repairing an existing model configuration Gallery template updates do not rewrite YAML files for already installed models. diff --git a/gallery/index.yaml b/gallery/index.yaml index 26e260b57..93a07b968 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -33574,6 +33574,150 @@ - filename: minicpm-v-4_6-mmproj-f16.gguf sha256: ca931d861d0801d9003e50697cd764721a334107c0e0415a51168ee1938462de uri: huggingface://openbmb/MiniCPM-V-4.6-gguf/mmproj-model-f16.gguf +- name: minicpm-v-4_7-1b-q4 + url: github:mudler/LocalAI/gallery/qwen3.yaml@master + urls: + - https://huggingface.co/openbmb/MiniCPM-V-4.7-1B + - https://huggingface.co/openbmb/MiniCPM-V-4.7-1B-gguf + description: | + MiniCPM-V 4.7 1B is OpenBMB's compact vision-language model for + text chat and image understanding. This entry uses the official + Q4_K_M GGUF weights and F16 vision projector through llama.cpp, + with an 8,192-token default context. + license: apache-2.0 + icon: https://avatars.githubusercontent.com/u/89920203 + tags: + - llm + - multimodal + - vision + - gguf + - cpu + - gpu + variants: + - model: minicpm-v-4_7-1b-q5 + - model: minicpm-v-4_7-1b-q6 + - model: minicpm-v-4_7-1b-q8 + overrides: + backend: llama-cpp + context_size: 8192 + known_usecases: + - chat + - vision + mmproj: llama-cpp/models/minicpm-v-4_7-1b/mmproj-model-f16.gguf + parameters: + model: llama-cpp/models/minicpm-v-4_7-1b/MiniCPM-V-4_7-1B-Q4_K_M.gguf + files: + - filename: llama-cpp/models/minicpm-v-4_7-1b/MiniCPM-V-4_7-1B-Q4_K_M.gguf + uri: https://huggingface.co/openbmb/MiniCPM-V-4.7-1B-gguf/resolve/59cd286146b6ce70f818508ccf512e11438d8957/MiniCPM-V-4_7-1B-Q4_K_M.gguf + sha256: 588c6c94c82f756b86dba35c42ed9ba9ec187d65824eb52f039c347df563e63d + - filename: llama-cpp/models/minicpm-v-4_7-1b/mmproj-model-f16.gguf + uri: https://huggingface.co/openbmb/MiniCPM-V-4.7-1B-gguf/resolve/59cd286146b6ce70f818508ccf512e11438d8957/mmproj-model-f16.gguf + sha256: fb9cc047a3cdad5317fd8433a4aeda2d22f00f02ca4bd93b34ad84165b25a900 +- name: minicpm-v-4_7-1b-q5 + url: github:mudler/LocalAI/gallery/qwen3.yaml@master + urls: + - https://huggingface.co/openbmb/MiniCPM-V-4.7-1B + - https://huggingface.co/openbmb/MiniCPM-V-4.7-1B-gguf + description: | + MiniCPM-V 4.7 1B is OpenBMB's compact vision-language model for + text chat and image understanding. This entry uses the official + Q5_K_M GGUF weights and F16 vision projector through llama.cpp, + with an 8,192-token default context. + license: apache-2.0 + icon: https://avatars.githubusercontent.com/u/89920203 + tags: + - llm + - multimodal + - vision + - gguf + - cpu + - gpu + overrides: + backend: llama-cpp + context_size: 8192 + known_usecases: + - chat + - vision + mmproj: llama-cpp/models/minicpm-v-4_7-1b/mmproj-model-f16.gguf + parameters: + model: llama-cpp/models/minicpm-v-4_7-1b/MiniCPM-V-4_7-1B-Q5_K_M.gguf + files: + - filename: llama-cpp/models/minicpm-v-4_7-1b/MiniCPM-V-4_7-1B-Q5_K_M.gguf + uri: https://huggingface.co/openbmb/MiniCPM-V-4.7-1B-gguf/resolve/59cd286146b6ce70f818508ccf512e11438d8957/MiniCPM-V-4_7-1B-Q5_K_M.gguf + sha256: ff7cf8926c8565b8d9e2ebfef8a5dd4cc8a2f34dc8b3c5b3eaa55fdc9e8b0a01 + - filename: llama-cpp/models/minicpm-v-4_7-1b/mmproj-model-f16.gguf + uri: https://huggingface.co/openbmb/MiniCPM-V-4.7-1B-gguf/resolve/59cd286146b6ce70f818508ccf512e11438d8957/mmproj-model-f16.gguf + sha256: fb9cc047a3cdad5317fd8433a4aeda2d22f00f02ca4bd93b34ad84165b25a900 +- name: minicpm-v-4_7-1b-q6 + url: github:mudler/LocalAI/gallery/qwen3.yaml@master + urls: + - https://huggingface.co/openbmb/MiniCPM-V-4.7-1B + - https://huggingface.co/openbmb/MiniCPM-V-4.7-1B-gguf + description: | + MiniCPM-V 4.7 1B is OpenBMB's compact vision-language model for + text chat and image understanding. This entry uses the official + Q6_K GGUF weights and F16 vision projector through llama.cpp, + with an 8,192-token default context. + license: apache-2.0 + icon: https://avatars.githubusercontent.com/u/89920203 + tags: + - llm + - multimodal + - vision + - gguf + - cpu + - gpu + overrides: + backend: llama-cpp + context_size: 8192 + known_usecases: + - chat + - vision + mmproj: llama-cpp/models/minicpm-v-4_7-1b/mmproj-model-f16.gguf + parameters: + model: llama-cpp/models/minicpm-v-4_7-1b/MiniCPM-V-4_7-1B-Q6_K.gguf + files: + - filename: llama-cpp/models/minicpm-v-4_7-1b/MiniCPM-V-4_7-1B-Q6_K.gguf + uri: https://huggingface.co/openbmb/MiniCPM-V-4.7-1B-gguf/resolve/59cd286146b6ce70f818508ccf512e11438d8957/MiniCPM-V-4_7-1B-Q6_K.gguf + sha256: ec9b0f9e041e7ca52a93cb2b7d98a439ac8bc70d0247cd33c03a9ae755e6a593 + - filename: llama-cpp/models/minicpm-v-4_7-1b/mmproj-model-f16.gguf + uri: https://huggingface.co/openbmb/MiniCPM-V-4.7-1B-gguf/resolve/59cd286146b6ce70f818508ccf512e11438d8957/mmproj-model-f16.gguf + sha256: fb9cc047a3cdad5317fd8433a4aeda2d22f00f02ca4bd93b34ad84165b25a900 +- name: minicpm-v-4_7-1b-q8 + url: github:mudler/LocalAI/gallery/qwen3.yaml@master + urls: + - https://huggingface.co/openbmb/MiniCPM-V-4.7-1B + - https://huggingface.co/openbmb/MiniCPM-V-4.7-1B-gguf + description: | + MiniCPM-V 4.7 1B is OpenBMB's compact vision-language model for + text chat and image understanding. This entry uses the official + Q8_0 GGUF weights and F16 vision projector through llama.cpp, + with an 8,192-token default context. + license: apache-2.0 + icon: https://avatars.githubusercontent.com/u/89920203 + tags: + - llm + - multimodal + - vision + - gguf + - cpu + - gpu + overrides: + backend: llama-cpp + context_size: 8192 + known_usecases: + - chat + - vision + mmproj: llama-cpp/models/minicpm-v-4_7-1b/mmproj-model-f16.gguf + parameters: + model: llama-cpp/models/minicpm-v-4_7-1b/MiniCPM-V-4_7-1B-Q8_0.gguf + files: + - filename: llama-cpp/models/minicpm-v-4_7-1b/MiniCPM-V-4_7-1B-Q8_0.gguf + uri: https://huggingface.co/openbmb/MiniCPM-V-4.7-1B-gguf/resolve/59cd286146b6ce70f818508ccf512e11438d8957/MiniCPM-V-4_7-1B-Q8_0.gguf + sha256: 2b83d8dfcd664c4dd9b9cfbe8dbd160782f2c6c362ca773758edc2dbc31420d7 + - filename: llama-cpp/models/minicpm-v-4_7-1b/mmproj-model-f16.gguf + uri: https://huggingface.co/openbmb/MiniCPM-V-4.7-1B-gguf/resolve/59cd286146b6ce70f818508ccf512e11438d8957/mmproj-model-f16.gguf + sha256: fb9cc047a3cdad5317fd8433a4aeda2d22f00f02ca4bd93b34ad84165b25a900 - &minicpm5-2b name: minicpm5-2b url: github:mudler/LocalAI/gallery/virtual.yaml@master