Instructions to use prithivMLmods/RoboAtom-Anno-9B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/RoboAtom-Anno-9B-GGUF with Transformers:

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/RoboAtom-Anno-9B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/RoboAtom-Anno-9B-GGUF 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 prithivMLmods/RoboAtom-Anno-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/RoboAtom-Anno-9B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/RoboAtom-Anno-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/RoboAtom-Anno-9B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf prithivMLmods/RoboAtom-Anno-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf prithivMLmods/RoboAtom-Anno-9B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/RoboAtom-Anno-9B-GGUF:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use prithivMLmods/RoboAtom-Anno-9B-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/RoboAtom-Anno-9B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use prithivMLmods/RoboAtom-Anno-9B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/RoboAtom-Anno-9B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "prithivMLmods/RoboAtom-Anno-9B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prithivMLmods/RoboAtom-Anno-9B-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/RoboAtom-Anno-9B-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/RoboAtom-Anno-9B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/RoboAtom-Anno-9B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.RoboAtom-Anno-9B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use prithivMLmods/RoboAtom-Anno-9B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/RoboAtom-Anno-9B-GGUF: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 prithivMLmods/RoboAtom-Anno-9B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prithivMLmods/RoboAtom-Anno-9B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/RoboAtom-Anno-9B-GGUF: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 "prithivMLmods/RoboAtom-Anno-9B-GGUF: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"

RoboAtom-Anno-9B-GGUF

RoboAtom-Anno-9B (InternRobotics/RoboAtom) is an Apache-2.0 open-weight video-text model based on Qwen/Qwen3.5-9B, developed by InternRobotics for temporal action segmentation and robot video annotation. Given manipulation videos and task instructions, it decomposes trajectories into ordered atomic actions, producing skill labels, action descriptions, and inclusive zero-based frame boundaries. Released in BF16, it supports multi-camera video processing and inference through the roboatom pipeline, with evaluation on RoboAtom-Bench. It serves as the compact 9B counterpart to the Qwen3.8-27B-based RoboAtom-Anno-27B. The provided description does not include benchmark scores.

MTP — Speculative Decoding: No

Model Files

File Name	Quant Type	File Size	File Link	Description
RoboAtom-Anno-9B.BF16.gguf	BF16	17.9 GB	Link	Full BF16 weights. Highest quality, largest file size.
RoboAtom-Anno-9B.Q3_K_L.gguf	Q3_K_L	4.93 GB	Link	Lower quality but usable, good for low RAM availability.
RoboAtom-Anno-9B.Q3_K_M.gguf	Q3_K_M	4.62 GB	Link	Low quality.
RoboAtom-Anno-9B.Q4_K_M.gguf	Q4_K_M	5.63 GB	Link	Good quality, default size for most use cases, recommended.
RoboAtom-Anno-9B.Q4_K_S.gguf	Q4_K_S	5.35 GB	Link	Slightly lower quality with more space savings, recommended.
RoboAtom-Anno-9B.Q5_K_M.gguf	Q5_K_M	6.47 GB	Link	High quality, recommended.
RoboAtom-Anno-9B.Q5_K_S.gguf	Q5_K_S	6.31 GB	Link	High quality, recommended.
RoboAtom-Anno-9B.Q6_K.gguf	Q6_K	7.36 GB	Link	Very high quality, near perfect, recommended.
RoboAtom-Anno-9B.Q8_0.gguf	Q8_0	9.53 GB	Link	Extremely high quality, generally unneeded but max available quant.
RoboAtom-Anno-9B.mmproj-bf16.gguf	mmproj-bf16	922 MB	Link	Multimodal projection file in BF16 format. Used for vision/language models.