Instructions to use prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-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/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4

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/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4
# Run inference directly in the terminal:
./build/bin/llama cli -hf prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4

Use Docker

docker model run hf.co/prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4

Llama new
LM Studio
Jan

vLLM

How to use prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-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/Llama-3.1-8B-Instruct-NVFP4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4

SGLang

How to use prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-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/Llama-3.1-8B-Instruct-NVFP4-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/Llama-3.1-8B-Instruct-NVFP4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/Llama-3.1-8B-Instruct-NVFP4-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/Llama-3.1-8B-Instruct-NVFP4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4
```
Unsloth Desktop

How to use prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-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/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4

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/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4
```

Lemonade

How to use prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4

Run and chat with the model

lemonade run user.Llama-3.1-8B-Instruct-NVFP4-GGUF-NVFP4

List all available models

lemonade list

Hermes Agent

How to use prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-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/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4

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/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prithivMLmods/Llama-3.1-8B-Instruct-NVFP4-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/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4

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/Llama-3.1-8B-Instruct-NVFP4-GGUF:NVFP4" \
  --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"

Llama-3.1-8B-Instruct-NVFP4-GGUF

Llama-3.1-8B-Instruct is Meta’s 8B text-only instruction-tuned model, released July 2024, with a 128K context window and grouped-query attention. Pretrained on approximately 15T publicly available tokens, it was aligned using supervised fine-tuning and RLHF for multilingual dialogue and tool use across eight supported languages. Key benchmark scores include 69.4 MMLU (73.0 with CoT), 48.3 MMLU-Pro, 80.4 IFEval, 30.4 GPQA, 72.6 HumanEval, 72.8 MBPP++, 84.5 GSM-8K, 51.9 MATH, 82.6 API-Bank, and 76.1 BFCL. Compared with Llama 3 8B Instruct, it improves substantially on math, coding, and tool use, including MATH (29.1 → 51.9), HumanEval (60.4 → 72.6), and API-Bank (48.3 → 82.6). Supports Transformers and original Llama checkpoints, with deployment safeguards recommended. Released under Meta’s custom Llama 3.1 Community License.

Model Files

File Name	Quant Type	File Size	File Link	Description
Llama-3.1-8B-Instruct-NVFP4-00001-of-00003.gguf	NVFP4	2.99 GB	Link	NVFP4 quantization (Shard 1/3). Highly optimized for NVIDIA Blackwell hardware accelerators (e.g., RTX Pro 6000, RTX 50-series, B200, B300), offering native hardware-accelerated FP4 Tensor Core speeds.
Llama-3.1-8B-Instruct-NVFP4-00002-of-00003.gguf	NVFP4	2 GB	Link	NVFP4 quantization (Shard 2/3).
Llama-3.1-8B-Instruct-NVFP4-00003-of-00003.gguf	NVFP4	1.05 GB	Link	NVFP4 quantization (Shard 3/3).

NVFP4 Test Run

Tested Llama-3.1-8B-Instruct-NVFP4-00001-of-00003.gguf on an NVIDIA RTX PRO 6000 Blackwell Server Edition GPU with 96 GB of VRAM, using llama-cli with full GPU offloading.

Performance Metrics

Metric	Value
Average Prompt Processing Speed	2,795.68 tokens/s
Average Generation Speed	206.87 tokens/s
Total Wall Time	19.2 seconds
Context Length	8,192 tokens
KV Cache (K)	`q8_0`
GPU	NVIDIA RTX PRO 6000 Blackwell Server Edition
GPU VRAM Capacity	96 GB
Peak GPU VRAM Usage	6.15 GiB
Peak GPU Utilization	92%
GPU Layers Offloaded	99 (`-ngl 99`)
Random Seed	42
Speculative Decoding	No
Test Runs	5

Test Shots

Shot	Test
Shot 1	C: Insert Node at End of Singly Linked List
Shot 2	Jogger and Train Passing Time
Shot 3	Two Pipes Filling a Tank
Shot 4	Students in Examination Rooms
Shot 5	Father and Son Ages

Run Inference

./build/bin/llama-cli \
  -m /path/to/models/Llama-3.1-8B-Instruct-NVFP4-00001-of-00003.gguf \
  -ngl 99 \
  -c 8192 \
  --cache-type-k q8_0 \
  --seed 42 \
  -n 4096 \
  -st \
  -p "Your prompt here"

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

llama.cpp

LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp

Snapshot(5)

The lineage mentioned in the snapshots is meta-llama/Llama-3.3-70B-Instruct, but it should actually be meta-llama/Llama-3.1-8B-Instruct. The lineage was incorrectly displayed in the snapshots.