Instructions to use prithivMLmods/d1-3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/d1-3B-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="prithivMLmods/d1-3B-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/d1-3B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/d1-3B-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/d1-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/d1-3B-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/d1-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/d1-3B-GGUF: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 prithivMLmods/d1-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/d1-3B-GGUF: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 prithivMLmods/d1-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/d1-3B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/d1-3B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/d1-3B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/d1-3B-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/d1-3B-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/d1-3B-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/d1-3B-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/d1-3B-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/d1-3B-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/d1-3B-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/d1-3B-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/d1-3B-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/d1-3B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use prithivMLmods/d1-3B-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/d1-3B-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/d1-3B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prithivMLmods/d1-3B-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/d1-3B-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/d1-3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/d1-3B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.d1-3B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use prithivMLmods/d1-3B-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/d1-3B-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/d1-3B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prithivMLmods/d1-3B-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/d1-3B-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/d1-3B-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"

d1-3B-GGUF

d1-3B is Liquid AI's 3.1-billion-parameter multimodal decision model, post-trained from LFM2.5-VL-3B to take a state (text, JSON, images, or a mix) plus a set of typed questions (noul yes/no, choice among named options, or score on an ordered scale) and return calibrated probabilities in one forward pass with zero generated output tokens — making it suited for routing, triage, moderation, intent/topic classification, extraction checks, reranking, LLM-as-a-judge scoring, agent guardrails, and visual inspection rather than open-ended chat. It retains the SigLIP2 NaFlex 400M vision encoder and 32,768-token context of its base model, and is notably fast: 8ms per decision on an RTX 4090, 9ms on an AMD MI325X, and 30ms on an Apple M5 Pro, with throughput reaching over 1,100 decisions/sec when 64 states are packed into one batch on the MI325X. On the Decision Index 0.2.1 it scores 48.57, the best model under 10B parameters, ahead of every 4B and 9B competitor as well as the much larger Decider 35B-A3B (47.11), with particularly strong Tools (74.5) and Arts (36.3) subscores, and across 11 public image benchmarks read as decisions it scores a 74.1 mean, slightly above its own base model (73.9), confirming the gains come from genuinely reading the images rather than text priors (removing images drops the same questions to 45.1). It's loaded via standard Transformers with trust_remote_code=True, callable through system_one() for single multi-question requests or system_one_batch() for padding-free batched inference, and is released under Liquid AI's LFM1.0 license. d1-3B on Hugging Face — https://huggingface.co/LiquidAI/d1-3B.

Model Files

File Name	Quant Type	File Size	File Link	Description
d1-3B.BF16.gguf	BF16	5.4 GB	Link	Full BF16 weights. Highest quality, largest file size.
d1-3B.Q3_K_L.gguf	Q3_K_L	1.45 GB	Link	Lower quality but usable, good for low RAM availability.
d1-3B.Q3_K_M.gguf	Q3_K_M	1.37 GB	Link	Low quality.
d1-3B.Q4_K_M.gguf	Q4_K_M	1.67 GB	Link	Good quality, default size for most use cases, recommended.
d1-3B.Q4_K_S.gguf	Q4_K_S	1.6 GB	Link	Slightly lower quality with more space savings, recommended.
d1-3B.Q5_K_M.gguf	Q5_K_M	1.94 GB	Link	High quality, recommended.
d1-3B.Q5_K_S.gguf	Q5_K_S	1.9 GB	Link	High quality, recommended.
d1-3B.Q6_K.gguf	Q6_K	2.22 GB	Link	Very high quality, near perfect, recommended.
d1-3B.mmproj-bf16.gguf	mmproj-bf16	856 MB	Link	Multimodal projection file in BF16 format. Used for vision/language models.