Instructions to use prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/Groot-19B-A3B-261023-MTP-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/Groot-19B-A3B-261023-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/Groot-19B-A3B-261023-MTP-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/Groot-19B-A3B-261023-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/Groot-19B-A3B-261023-MTP-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/Groot-19B-A3B-261023-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF:Q4_K_M
```
Unsloth Desktop

How to use prithivMLmods/Groot-19B-A3B-261023-MTP-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/Groot-19B-A3B-261023-MTP-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/Groot-19B-A3B-261023-MTP-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/Groot-19B-A3B-261023-MTP-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Groot-19B-A3B-261023-MTP-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use prithivMLmods/Groot-19B-A3B-261023-MTP-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/Groot-19B-A3B-261023-MTP-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/Groot-19B-A3B-261023-MTP-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prithivMLmods/Groot-19B-A3B-261023-MTP-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/Groot-19B-A3B-261023-MTP-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/Groot-19B-A3B-261023-MTP-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"

Groot-19B-A3B-261023-MTP-GGUF

Groot-19B-A3B-261023 is a compact, open-weight (Apache-2.0), natively multimodal Mixture-of-Experts (MoE) reasoning model built for complex real-world tasks, agentic coding, and native tool use. Derived from Qwen3.6-35B-A3B and post-trained on fewer than 0.1 billion open-source tokens, it comprises roughly 19B total parameters (plus a 0.4B Multi-Token Prediction layer) with only ~3B activated per token across 40 hybrid layers (10 full-attention and 30 linear-attention) and 128 routed experts. Despite using 45.7% fewer parameters than Qwen3.6-35B-A3B and 26.9% fewer than Gemma-4-26B-A4B, it outperforms both on 12 of 16 benchmarks (averaging 41.44 vs. 38.08 and 30.05) while consuming 23.1% and 65.6% fewer output tokens, respectively. The model operates in thinking mode by default—with configurable non-thinking and preserved-thinking modes—and supports a native 262,144-token (256K) context window extensible to roughly 1M tokens via YaRN. Released in BF16, FP8, NVFP4, and GGUF (Q4_K_M) weights for deployment on vLLM, SGLang, KTransformers, and Hugging Face Transformers, it is engineered for accessible hardware, running a 128K context on a 16GB RTX 4060 Ti and the full 256K context on 24GB consumer GPUs (RTX 3090/4090), an RTX 5090, or 128GB unified-memory systems.

MTP — Speculative Decoding: Yes

Multi-Token Prediction (MTP) GGUF is a specialized GGUF model file format extension that integrates speculative decoding directly into the model weights to significantly accelerate local inference. Unlike traditional speculative decoding which requires a separate, smaller "draft" model, MTP GGUF files include additional output heads within the main model architecture that predict multiple future tokens in a single forward pass.

Model Files

File Name	Quant Type	File Size	File Link	Description
Groot-19B-A3B-261023.BF16.gguf	BF16	38 GB	Link	Full BF16 weights. Highest quality, largest file size.
Groot-19B-A3B-261023.Q3_K_L.gguf	Q3_K_L	10 GB	Link	Lower quality but usable, good for low RAM availability.
Groot-19B-A3B-261023.Q3_K_M.gguf	Q3_K_M	9.27 GB	Link	Low quality.
Groot-19B-A3B-261023.Q4_K_M.gguf	Q4_K_M	11.7 GB	Link	Good quality, default size for most use cases, recommended.
Groot-19B-A3B-261023.Q4_K_S.gguf	Q4_K_S	11 GB	Link	Slightly lower quality with more space savings, recommended.
Groot-19B-A3B-261023.Q5_K_M.gguf	Q5_K_M	13.6 GB	Link	High quality, recommended.
Groot-19B-A3B-261023.Q5_K_S.gguf	Q5_K_S	13.2 GB	Link	High quality, recommended.
Groot-19B-A3B-261023.Q6_K.gguf	Q6_K	15.6 GB	Link	Very high quality, near perfect, recommended.
Groot-19B-A3B-261023.mmproj-bf16.gguf	mmproj-bf16	903 MB	Link	Multimodal projection file in BF16 format. Used for vision/language models.

BF16 Test Run

Tested Groot-19B-A3B-261023.BF16.gguf with vision support on an NVIDIA RTX PRO 6000 Blackwell Server Edition GPU with 96 GB VRAM, using llama-cli with full GPU offloading and MTP speculative decoding.

Performance Metrics

Metric	Result
Average Prefill Speed	165.32 tokens/s
Average Decode Speed	197.13 tokens/s
Minimum Decode Speed	188.10 tokens/s
Maximum Decode Speed	205.44 tokens/s
Average Wall Time	14.55 s
Total Wall Time	72.7 s
Total Generated Tokens	7,757
Peak VRAM Usage	36,807 MiB (35.94 GiB)
Maximum GPU Utilization	89%
Completed Runs	5/5

Test Shots

#	Task	Prefill (t/s)	Decode (t/s)	Generated Tokens	Wall Time
1	C: Insert Node at End of Singly Linked List	86.17	194.37	2,333	19.03 s
2	Jogger and Train Passing Time	190.27	188.10	2,170	18.57 s
3	Two Pipes Filling a Tank	171.69	205.44	1,103	11.62 s
4	Students in Examination Rooms	229.48	197.34	1,256	12.72 s
5	Father and Son Ages	149.01	200.41	895	10.79 s

Run Inference

llama-cli \
    -m /path/to/models/Groot-19B-A3B-261023.BF16.gguf \
    --spec-type draft-mtp \
    --spec-draft-n-max 2 \
    -ngl 99 \
    -c 16384 \
    --cache-type-k q8_0 \
    --seed 42 \
    -n 8192 \
    -st \
    -p "Write a program in C to insert a new node at the end of a Singly Linked List."

Performance results reflect this specific hardware and inference configuration. Actual throughput may vary depending on the prompt, output length, model, software build, and runtime settings.