Instructions to use anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF",
	filename="Eve-2-MoE-NanoFunction-272M-Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf anthonym21/Eve-2-MoE-NanoFunction-272M-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 anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf anthonym21/Eve-2-MoE-NanoFunction-272M-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 anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF with Ollama:
```
ollama run hf.co/anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF:Q4_K_M
```

Unsloth Studio new

How to use anthonym21/Eve-2-MoE-NanoFunction-272M-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 anthonym21/Eve-2-MoE-NanoFunction-272M-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 anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF to start chatting

Docker Model Runner
How to use anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF with Docker Model Runner:
```
docker model run hf.co/anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF:Q4_K_M
```

Lemonade

How to use anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Eve-2-MoE-NanoFunction-272M-GGUF-Q4_K_M

List all available models

lemonade list

Eve-2-MoE-NanoFunction-272M - GGUF

GGUF quantizations of anthonym21/Eve-2-MoE-NanoFunction-272M.

Quantization Variants

Quantization	Filename	Size
Q8_0	Eve-2-MoE-NanoFunction-272M-Q8_0.gguf	290.9 MB
Q4_K_M	Eve-2-MoE-NanoFunction-272M-Q4_K_M.gguf	189.5 MB

Usage with Ollama

ollama run anthonym21/eve-2-moe-nanofunction-272m

Usage with llama.cpp

llama-cli -m Eve-2-MoE-NanoFunction-272M-Q4_K_M.gguf -p "Your prompt here"

Architecture

Type: DeepSeek-style Mixture of Experts (MoE)
Parameters: 272M total
Layers: 12
Hidden dim: 512
Experts: 8 routed (top-2) + 1 shared per layer
Context: 2048 tokens
Tokenizer: GPT-2

Parent Model

This is a quantized version of anthonym21/Eve-2-MoE-NanoFunction-272M.

Downloads last month: 7

GGUF

Model size

0.3B params

Architecture

deepseek

Hardware compatibility

4-bit

8-bit

Inference Providers NEW

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

Model tree for anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF

Base model

anthonym21/Eve-2-MoE-272M

Finetuned

anthonym21/Eve-2-MoE-IT-272M

Finetuned

anthonym21/Eve-2-MoE-NanoFunction-272M

Quantized

(1)

this model

Collection including anthonym21/Eve-2-MoE-NanoFunction-272M-GGUF

Eve 2

Collection

Eve 2 family of models; 272M parameter MoE IT Specialist Agents • 19 items • Updated Feb 10 • 1