Instructions to use ramankrishna10/npc-nano-0.5b-sft-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ramankrishna10/npc-nano-0.5b-sft-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ramankrishna10/npc-nano-0.5b-sft-gguf",
	filename="npc-nano-0.5b-sft.f16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ramankrishna10/npc-nano-0.5b-sft-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 ramankrishna10/npc-nano-0.5b-sft-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ramankrishna10/npc-nano-0.5b-sft-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 ramankrishna10/npc-nano-0.5b-sft-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ramankrishna10/npc-nano-0.5b-sft-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 ramankrishna10/npc-nano-0.5b-sft-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ramankrishna10/npc-nano-0.5b-sft-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 ramankrishna10/npc-nano-0.5b-sft-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ramankrishna10/npc-nano-0.5b-sft-gguf:Q4_K_M

Use Docker

docker model run hf.co/ramankrishna10/npc-nano-0.5b-sft-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use ramankrishna10/npc-nano-0.5b-sft-gguf with Ollama:
```
ollama run hf.co/ramankrishna10/npc-nano-0.5b-sft-gguf:Q4_K_M
```

Unsloth Studio

How to use ramankrishna10/npc-nano-0.5b-sft-gguf 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 ramankrishna10/npc-nano-0.5b-sft-gguf 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 ramankrishna10/npc-nano-0.5b-sft-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ramankrishna10/npc-nano-0.5b-sft-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use ramankrishna10/npc-nano-0.5b-sft-gguf with Docker Model Runner:
```
docker model run hf.co/ramankrishna10/npc-nano-0.5b-sft-gguf:Q4_K_M
```

Lemonade

How to use ramankrishna10/npc-nano-0.5b-sft-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ramankrishna10/npc-nano-0.5b-sft-gguf:Q4_K_M

Run and chat with the model

lemonade run user.npc-nano-0.5b-sft-gguf-Q4_K_M

List all available models

lemonade list

NPC Nano 0.5B — SFT — GGUF quants

GGUF quantizations of ramankrishna10/npc-nano-0.5b-sft for use with llama.cpp and compatible inference tools (Ollama, LM Studio, Jan, etc.).

File	Bits / scheme	Size	Notes
`npc-nano-0.5b-sft.f16.gguf`	fp16	1.00 GB	reference; full precision
`npc-nano-0.5b-sft.q8_0.gguf`	8-bit (legacy)	534 MB	smallest quality loss
`npc-nano-0.5b-sft.q5_k_m.gguf`	5-bit (k-quant)	379 MB	recommended default for desktop CPU
`npc-nano-0.5b-sft.q4_k_m.gguf`	4-bit (k-quant)	333 MB	most aggressive; tested working

All quants verified emitting correct identity ("I'm NPC Nano, a 0.5B parameter model by Rama Krishna Bachu at Bottensor.") under greedy decoding.

Usage

llama-cli (interactive)

./llama-cli -m npc-nano-0.5b-sft.q5_k_m.gguf

Ollama

ollama create npc-nano -f Modelfile     # Modelfile points to a quant
ollama run npc-nano "Who built you?"

LM Studio / Jan

Drop any .gguf into the models directory and select via the UI.

Chat template

Standard ChatML, baked into the GGUF:

<|im_start|>user
Who built you?<|im_end|>
<|im_start|>assistant

The GGUF metadata includes the chat template so client tools (Ollama, LM Studio) apply it automatically.

Source

Full safetensors weights and model card: ramankrishna10/npc-nano-0.5b-sft
Pretrain base: ramankrishna10/npc-nano-0.5b-base
Paper: forthcoming on Zenodo
License: Apache 2.0

Acknowledgments

Quants produced via llama.cpp convert_hf_to_gguf.py + llama-quantize.

Downloads last month: 16

GGUF

Model size

0.5B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ramankrishna10/npc-nano-0.5b-sft-gguf

Base model

ramankrishna10/npc-nano-0.5b-base

Finetuned

ramankrishna10/npc-nano-0.5b-sft

Quantized

(1)

this model