From 99d816959b3f7a810b93036fba4ee371fde57fb3 Mon Sep 17 00:00:00 2001
From: localai-org-maint-bot
 <306269227+localai-org-maint-bot@users.noreply.github.com>
Date: Tue, 11 Aug 2026 12:06:04 +0000
Subject: [PATCH] feat(gallery): add Supra2 100M Instruct

Add the official F16 GGUF build of the compact Apache-2.0 Qwen3-family chat model with its native 2K context limit.

Assisted-by: Codex:gpt-5
---
 gallery/index.yaml | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/gallery/index.yaml b/gallery/index.yaml
index 40c9210b7428..670b133515cf 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -1,4 +1,33 @@
 ---
+- name: "supra2-100m-instruct"
+  url: "github:mudler/LocalAI/gallery/qwen3.yaml@master"
+  urls:
+    - https://huggingface.co/SupraLabs/Supra2-100M-Instruct
+  description: |
+    Supra2-100M-Instruct is a compact English chat model trained from scratch by
+    SupraLabs on the Qwen3 architecture. It has 100 million parameters, a
+    2,048-token context window, and is intended for lightweight experiments and
+    constrained edge deployments. This entry uses the publisher's official F16
+    GGUF build.
+  license: "apache-2.0"
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - chat
+    - qwen3
+    - edge
+    - english
+  last_checked: "2026-08-11"
+  overrides:
+    parameters:
+      context_size: 2048
+      model: Supra2-100M-SFT-F16.gguf
+  files:
+    - filename: Supra2-100M-SFT-F16.gguf
+      uri: huggingface://SupraLabs/Supra2-100M-Instruct/Supra2-100M-SFT-F16.gguf
+      sha256: f88228c3dcc13b5ee2333cbb6fc2416de908e5b8adabd39bf9ee4378f28451eb
 - &qwen3-8-27b
   name: "qwen3.8-27b-q4"
   variants: