feat: Add Breeze 3B Q4 model (mradermacher/breeze-3b-GGUF)

- Added Breeze 3B with Q4_K_M quantization (2.0GB)
- 32K context window based on Qwen2.5-Coder architecture
- Updated README: 22→23 models

README.md

@@ -12,11 +12,11 @@ license: mit
 
 # Tiny Scribe
 
-A lightweight transcript summarization tool powered by local LLMs. Features 22 models ranging from 100M to 30B parameters with live streaming output, reasoning modes, and flexible deployment options.
+A lightweight transcript summarization tool powered by local LLMs. Features 23 models ranging from 100M to 30B parameters with live streaming output, reasoning modes, and flexible deployment options.
 
 ## Features
 
-- **22 Local Models**: From tiny 100M models to powerful 30B models
+- **23 Local Models**: From tiny 100M models to powerful 30B models
 - **Live Streaming**: Real-time summary generation with token-by-token output
 - **Model Selection**: Dropdown to choose from 22 available models
 - **Reasoning Modes**: Toggle thinking/reasoning for supported models (Qwen3, ERNIE, LFM2)
@@ -26,7 +26,7 @@ A lightweight transcript summarization tool powered by local LLMs. Features 22 m
 - **Language Support**: English or Traditional Chinese (zh-TW) output via OpenCC
 - **Auto Settings**: Temperature, top_p, and top_k sliders auto-populate per model
 
-## Model Registry (22 Models)
+## Model Registry (23 Models)
 
 ### Tiny Models (0.1-0.6B)
 - **Falcon-H1-100M** - 100M parameters, 4K context
@@ -48,6 +48,7 @@ A lightweight transcript summarization tool powered by local LLMs. Features 22 m
 
 ### Standard Models (3-7B)
 - **Granite-3.1-3B-A800M** - 3B parameters, 4K context
+- **Breeze-3B-Q4** - 3B parameters, 32K context
 - **Qwen3-4B-Thinking** - 4B parameters, 8K context (reasoning)
 - **Granite-4.0-Tiny-7B** - 7B parameters, 8K context
 
@@ -61,7 +62,7 @@ A lightweight transcript summarization tool powered by local LLMs. Features 22 m
 ## Usage
 
 1. **Select Output Language**: Choose English or Traditional Chinese (zh-TW)
-2. **Select Model**: Choose from the dropdown of 22 available models
+2. **Select Model**: Choose from the dropdown of 23 available models
 3. **Configure Settings** (optional):
    - Enable "Use Reasoning Mode" for thinking models
    - Adjust Temperature, Top-p, and Top-k (auto-populated per model)

app.py

@@ -218,6 +218,20 @@ AVAILABLE_MODELS = {
             "repeat_penalty": 1.1,
         },
     },
+    "breeze_3b_q4": {
+        "name": "Breeze 3B Q4 (32K Context)",
+        "repo_id": "mradermacher/breeze-3b-GGUF",
+        "filename": "*Q4_K_M.gguf",
+        "max_context": 32768,
+        "default_temperature": 0.6,
+        "supports_toggle": False,
+        "inference_settings": {
+            "temperature": 0.6,
+            "top_p": 0.95,
+            "top_k": 20,
+            "repeat_penalty": 1.0,
+        },
+    },
     "granite_3_1_3b_q4": {
         "name": "Granite 3.1 3B-A800M Instruct (128K Context)",
         "repo_id": "bartowski/granite-3.1-3b-a800m-instruct-GGUF",