feat(gallery): add MiniCPM5 2B F16 variant

Offer the official F16 build alongside Q4 and Q8, with a pinned download
and an explicit installation example.

Assisted-by: Codex:gpt-6

docs/content/features/model-gallery.md

@@ -64,6 +64,19 @@ The [source model](https://huggingface.co/XHToken/Spark-X2.5-1.7B) supports up t
 1,048,576 tokens; larger contexts require more memory. Use a current LocalAI
 llama.cpp backend with Spark-X2.5 support.
 
+## MiniCPM5-2B
+
+MiniCPM5-2B offers the official Q4_K_M, Q8_0, and F16 GGUF builds through
+llama.cpp. To install the F16 build explicitly:
+
+```bash
+local-ai models install minicpm5-2b --variant minicpm5-2b-f16
+```
+
+The F16 weights require a 5.04 GB download, plus additional memory for inference.
+This entry uses the embedded chat template and an 8,192-token context.
+See the [official GGUF repository](https://huggingface.co/openbmb/MiniCPM5-2B-GGUF).
+
 ## VRAM and download size estimates
 
 When browsing the gallery or importing a model by URI, LocalAI can show **estimated download size** and **estimated VRAM** for models.

gallery/index.yaml

@@ -27155,6 +27155,7 @@
     Q4_K_M GGUF quantization and the model's embedded chat template.
   variants:
     - model: minicpm5-2b-q8
+    - model: minicpm5-2b-f16
   overrides:
     backend: llama-cpp
     known_usecases:
@@ -27196,6 +27197,30 @@
     - filename: llama-cpp/models/minicpm5-2b/MiniCPM5-2B-Q8_0.gguf
       uri: huggingface://openbmb/MiniCPM5-2B-GGUF/MiniCPM5-2B-Q8_0.gguf
       sha256: c5415f8989bf88a8288f1b55a3cc371af53c07b0faa220a63bd7a990cfaba078
+- !!merge <<: *minicpm5-2b
+  name: minicpm5-2b-f16
+  description: |
+    MiniCPM5-2B is OpenBMB's compact Llama-based language model for English
+    and Chinese chat, coding, and reasoning. This entry uses the official
+    F16 GGUF build and the model's embedded chat template.
+  variants: null
+  overrides:
+    backend: llama-cpp
+    context_size: 8192
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    template:
+      use_tokenizer_template: true
+    parameters:
+      model: llama-cpp/models/minicpm5-2b/MiniCPM5-2B-F16.gguf
+      temperature: 1.0
+      top_p: 0.95
+  files:
+    - filename: llama-cpp/models/minicpm5-2b/MiniCPM5-2B-F16.gguf
+      uri: https://huggingface.co/openbmb/MiniCPM5-2B-GGUF/resolve/2079a22f3beaa4e306449978533478fe0522f4b3/MiniCPM5-2B-F16.gguf
+      sha256: 0ffba3682a853295566b98bc38c0ab755d6b2d91b994bc031ed727a08cfcdf25
 - &minicpm5-1b
   name: minicpm5-1b
   url: github:mudler/LocalAI/gallery/chatml.yaml@master