From 03020bce15591a387d6b657aaeaadab60c24c7d8 Mon Sep 17 00:00:00 2001
From: localai-org-maint-bot
 <306269227+localai-org-maint-bot@users.noreply.github.com>
Date: Sat, 12 Sep 2026 20:07:26 +0000
Subject: [PATCH] feat(gallery): add NeoHorse-1-4B variants

Offer Q4, Q6, and Q8 GGUF builds with pinned downloads and verified hashes.
Use the embedded chat template and document installation.

Assisted-by: Codex:gpt-6
---
 docs/content/features/model-gallery.md |  19 +++++
 gallery/index.yaml                     | 101 +++++++++++++++++++++++++
 2 files changed, 120 insertions(+)

diff --git a/docs/content/features/model-gallery.md b/docs/content/features/model-gallery.md
index 4cd6f719a..4db1c67fe 100644
--- a/docs/content/features/model-gallery.md
+++ b/docs/content/features/model-gallery.md
@@ -43,6 +43,25 @@ Both views use the same model selection and 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.
 
+## NeoHorse-1-4B
+
+Install NeoHorse-1-4B with automatic selection between Q4_K_M, Q6_K, and Q8_0 GGUF builds:
+
+```bash
+local-ai models install neohorse-1-4b-q4
+```
+
+To select Q8_0 explicitly:
+
+```bash
+local-ai models install neohorse-1-4b-q4 --variant neohorse-1-4b-q8
+```
+
+[NeoHorse-1-4B](https://huggingface.co/TokenRhythm/NeoHorse-1-4B) is a text-only Qwen3.5 fine-tune for coding, reasoning, and agentic tasks.
+These builds use llama.cpp and the embedded Jinja chat template.
+The gallery defaults to 32,768 context tokens; the model supports up to 262,144 tokens with sufficient memory.
+The [GGUF downloads](https://huggingface.co/mradermacher/NeoHorse-1-4B-GGUF) are pinned to a revision and verified with SHA256 checksums.
+
 ## Spark-X2.5-1.7B
 
 Install Spark-X2.5-1.7B with automatic selection between its Q4_K_M and Q8_0
diff --git a/gallery/index.yaml b/gallery/index.yaml
index 5b0139e72..66e997b6b 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -14291,6 +14291,107 @@
     - filename: llama-cpp/mmproj/mmproj-Qwen_Qwen3.5-2B-f16.gguf
       sha256: 044a0ea136cca70711ae16e23b24d754b44eab6f2462d187aee4d7c7a9503d36
       uri: https://huggingface.co/bartowski/Qwen_Qwen3.5-2B-GGUF/resolve/main/mmproj-Qwen_Qwen3.5-2B-f16.gguf
+- &neohorse-1-4b
+  name: neohorse-1-4b-q4
+  url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  urls:
+    - https://huggingface.co/TokenRhythm/NeoHorse-1-4B
+    - https://huggingface.co/mradermacher/NeoHorse-1-4B-GGUF
+  license: apache-2.0
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - reasoning
+    - coding
+  variants:
+    - model: neohorse-1-4b-q6
+    - model: neohorse-1-4b-q8
+  description: |
+    NeoHorse-1-4B is TokenRhythm's text-only Qwen3.5-4B fine-tune for coding,
+    reasoning, and agentic tasks. This build uses Q4_K_M GGUF weights with
+    the embedded Jinja chat template and a 32K-token default context.
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: NeoHorse-1-4B.Q4_K_M.gguf
+      temperature: 1
+      top_p: 0.95
+      top_k: 20
+      min_p: 0
+      presence_penalty: 1.5
+      repeat_penalty: 1
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: NeoHorse-1-4B.Q4_K_M.gguf
+      uri: https://huggingface.co/mradermacher/NeoHorse-1-4B-GGUF/resolve/926d357de701ecf787324228734866faaf02054e/NeoHorse-1-4B.Q4_K_M.gguf
+      sha256: 9a8426d0a5a1035d7e35ccc02794c404e027cca8e51f936b225d26d93bc44753
+
+- !!merge <<: *neohorse-1-4b
+  name: neohorse-1-4b-q6
+  variants: []
+  description: |
+    NeoHorse-1-4B is TokenRhythm's text-only Qwen3.5-4B fine-tune for coding,
+    reasoning, and agentic tasks. This build uses Q6_K GGUF weights with
+    the embedded Jinja chat template and a 32K-token default context.
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: NeoHorse-1-4B.Q6_K.gguf
+      temperature: 1
+      top_p: 0.95
+      top_k: 20
+      min_p: 0
+      presence_penalty: 1.5
+      repeat_penalty: 1
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: NeoHorse-1-4B.Q6_K.gguf
+      uri: https://huggingface.co/mradermacher/NeoHorse-1-4B-GGUF/resolve/926d357de701ecf787324228734866faaf02054e/NeoHorse-1-4B.Q6_K.gguf
+      sha256: d29d06d4b778b21a4b7145428ba5d709bf368fc6dc7321e0af3463c1718fec41
+
+- !!merge <<: *neohorse-1-4b
+  name: neohorse-1-4b-q8
+  variants: []
+  description: |
+    NeoHorse-1-4B is TokenRhythm's text-only Qwen3.5-4B fine-tune for coding,
+    reasoning, and agentic tasks. This build uses Q8_0 GGUF weights with
+    the embedded Jinja chat template and a 32K-token default context.
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: NeoHorse-1-4B.Q8_0.gguf
+      temperature: 1
+      top_p: 0.95
+      top_k: 20
+      min_p: 0
+      presence_penalty: 1.5
+      repeat_penalty: 1
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: NeoHorse-1-4B.Q8_0.gguf
+      uri: https://huggingface.co/mradermacher/NeoHorse-1-4B-GGUF/resolve/926d357de701ecf787324228734866faaf02054e/NeoHorse-1-4B.Q8_0.gguf
+      sha256: ec5e02b4d3a102335333a692b1b83ee454e249e06a6d27f00b2f5bc81a199c98
+
 - name: qwen_qwen3.5-4b
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls: