Instructions to use addyo07/vox-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use addyo07/vox-models with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf addyo07/vox-models:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf addyo07/vox-models:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf addyo07/vox-models:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf addyo07/vox-models:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf addyo07/vox-models:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf addyo07/vox-models:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf addyo07/vox-models:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf addyo07/vox-models:Q4_K_M

Use Docker

docker model run hf.co/addyo07/vox-models:Q4_K_M

LM Studio
Jan
Ollama
How to use addyo07/vox-models with Ollama:
```
ollama run hf.co/addyo07/vox-models:Q4_K_M
```

Unsloth Studio

How to use addyo07/vox-models with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for addyo07/vox-models to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for addyo07/vox-models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for addyo07/vox-models to start chatting

How to use addyo07/vox-models with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf addyo07/vox-models:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "addyo07/vox-models:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use addyo07/vox-models with Docker Model Runner:
```
docker model run hf.co/addyo07/vox-models:Q4_K_M
```

Lemonade

How to use addyo07/vox-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull addyo07/vox-models:Q4_K_M

Run and chat with the model

lemonade run user.vox-models-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use addyo07/vox-models with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf addyo07/vox-models:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default addyo07/vox-models:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use addyo07/vox-models with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf addyo07/vox-models:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "addyo07/vox-models:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

addy-hypr4 commited on 6 days ago

Commit

bcfbf2d

1 Parent(s): b64f835

feat: changes default base llm from llama to qwen

Browse files

Files changed (1) hide show

models_manifest.json +11 -57

models_manifest.json CHANGED Viewed

@@ -192,71 +192,25 @@
       ]
     },
     {
-      "id": "gemma_4_reasoning",
-      "name": "Gemma 4 Reasoning LLM",
       "category": "llm",
       "subcategory": "main",
-      "description": "Smart conversational engine. Great balance of speed and intelligence for general tasks.",
-      "parameters": "2.4B (Q4_K_M)",
-      "ram_usage": "~1.4 GB",
-      "tradeoffs": "Supports tool calling and smart reasoning",
       "version": "1.0.0",
       "is_built_in": false,
       "is_cloud": false,
       "is_remote": false,
       "files": [
         {
-          "id": "llm_gemma_4_q4_k_m",
-          "path": "llm/gemma4/gemma-4-e2b-q4_k_m.gguf",
-          "size": 3462678272,
-          "sha256": "b5310340b3a23d31655d7119d100d5df1b2d8ee17b3ca8b0a23ad7e9eb5fa705",
-          "required": false
-        }
-      ]
-    },
-    {
-      "id": "llama_3_2_reasoning_q4",
-      "name": "Llama 3.2 1B (Q4)",
-      "category": "llm",
-      "subcategory": "main",
-      "description": "Fast and concise model. Optimized for ultra-low latency quick replies.",
-      "parameters": "1.2B (Q4_K_M)",
-      "ram_usage": "~750 MB",
-      "tradeoffs": "Ultra-fast response time; lightweight",
-      "version": "1.0.0",
-      "is_built_in": false,
-      "is_cloud": false,
-      "is_remote": false,
-      "files": [
-        {
-          "id": "llm_llama_3_2_1b_instruct_q4_k_m",
-          "path": "llm/llama/llama-3.2-1b-q4_k_m.gguf",
-          "size": 807694464,
-          "sha256": "6f85a640a97cf2bf5b8e764087b1e83da0fdb51d7c9fab7d0fece9385611df83",
-          "required": false
-        }
-      ]
-    },
-    {
-      "id": "llama_3_2_reasoning",
-      "name": "Llama 3.2 1B (Q6)",
-      "category": "llm",
-      "subcategory": "main",
-      "description": "Higher precision model. Delivers detailed, high-fidelity answers.",
-      "parameters": "1.2B (Q6_K)",
-      "ram_usage": "~1.0 GB",
-      "tradeoffs": "Higher output fidelity; slightly slower response",
-      "version": "1.0.0",
-      "is_built_in": false,
-      "is_cloud": false,
-      "is_remote": false,
-      "files": [
-        {
-          "id": "llm_llama_3_2_1b_instruct_q6_k",
-          "path": "llm/llama/llama-3.2-1b-q6_k.gguf",
-          "size": 1021800576,
-          "sha256": "0f4c510daf16e0d1b3bc94931fd9296c28936bebdda2593687d4eb70c5b70628",
-          "required": false
         }
       ]
     },

       ]
     },
     {
+      "id": "qwen_3_5_0_8b",
+      "name": "Qwen 3.5 0.8B (Q4)",
       "category": "llm",
       "subcategory": "main",
+      "description": "Ultra-fast and intelligent multilingual conversational engine with official ChatML template.",
+      "parameters": "0.8B (Q4_K_M)",
+      "ram_usage": "~550 MB",
+      "tradeoffs": "Extremely fast TTFT and high throughput for English and Hindi conversational inference",
       "version": "1.0.0",
       "is_built_in": false,
       "is_cloud": false,
       "is_remote": false,
       "files": [
         {
+          "id": "llm_qwen_3_5_0_8b_q4_k_m",
+          "path": "llm/qwen/qwen-3.5-0.8b-q4_k_m.gguf",
+          "size": 532517120,
+          "sha256": "bd258782e35f7f458f8aced1adc053e6e92e89bc735ba3be89d38a06121dc517",
+          "required": true
         }
       ]
     },