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

Libraries

How to use RefinedNeuro/VibeThinker-3B-Hermes-GGUF with HERMES:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

llama-cpp-python

How to use RefinedNeuro/VibeThinker-3B-Hermes-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RefinedNeuro/VibeThinker-3B-Hermes-GGUF",
	filename="VibeThinker-3B-Hermes-Q6_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use RefinedNeuro/VibeThinker-3B-Hermes-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 RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K

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 RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K

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 RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K

Use Docker

docker model run hf.co/RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K

LM Studio
Jan

vLLM

How to use RefinedNeuro/VibeThinker-3B-Hermes-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RefinedNeuro/VibeThinker-3B-Hermes-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": "RefinedNeuro/VibeThinker-3B-Hermes-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K

Ollama
How to use RefinedNeuro/VibeThinker-3B-Hermes-GGUF with Ollama:
```
ollama run hf.co/RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K
```

Unsloth Studio

How to use RefinedNeuro/VibeThinker-3B-Hermes-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 RefinedNeuro/VibeThinker-3B-Hermes-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 RefinedNeuro/VibeThinker-3B-Hermes-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RefinedNeuro/VibeThinker-3B-Hermes-GGUF to start chatting

How to use RefinedNeuro/VibeThinker-3B-Hermes-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use RefinedNeuro/VibeThinker-3B-Hermes-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 RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K

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 RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use RefinedNeuro/VibeThinker-3B-Hermes-GGUF with Docker Model Runner:
```
docker model run hf.co/RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K
```

Lemonade

How to use RefinedNeuro/VibeThinker-3B-Hermes-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RefinedNeuro/VibeThinker-3B-Hermes-GGUF:Q6_K

Run and chat with the model

lemonade run user.VibeThinker-3B-Hermes-GGUF-Q6_K

List all available models

lemonade list

VibeThinker-3B-Hermes — GGUF (Research Preview)

⚠️ Research preview / experimental. Read Limitations before use. Known issues: repetition loops on out-of-distribution multi-turn input, and over-eagerness to call tools.

GGUF quantizations of a LoRA fine-tune of WeiboAI/VibeThinker-3B that adds Hermes-style function calling (<think>…</think> + <tool_call>…</tool_call>) while preserving reasoning. See the full (transformers) model card for training details and benchmarks.

Files

File	Quant	Size
`…-Q6_K.gguf`	Q6_K	2.4 GB
`…-Q8_0.gguf`	Q8_0	3.1 GB
`…-f16.gguf`	F16	5.8 GB

Why only Q6_K and up? We measured tool-call fidelity on a multi-step agentic task: Q6_K, Q8_0 and F16 pass; Q3/Q4/Q5 fail (they emit malformed/incomplete tool calls and can loop). Since this is a tool-calling model, the lower quants were removed to avoid shipping a broken experience. Use Q6_K for the best size/quality balance.

Usage (llama.cpp)

# use Q6_K+ for tool-calling
llama-cli -m VibeThinker-3B-Hermes-Q6_K.gguf \
  --temp 0.6 --top-p 0.95 --repeat-penalty 1.1 \
  -p "<your Hermes-formatted prompt>"

Recommended settings

Use a stop on </tool_call> for single-call settings — essential to avoid the model appending duplicate/hallucinated calls.
temperature 0.6, top_p 0.95, repeat-penalty ≈ 1.1.
Stop tokens: <|im_end|> (151645) and <|endoftext|> (151643).
Hermes system prompt with a <tools> block; the model emits <think>…</think> then <tool_call>\n{"name": …, "arguments": …}\n</tool_call>.

Benchmarks (summary)

Reasoning (AIME 2024): base avg@4 0.842 → this model 0.783; pass@4 0.867 unchanged.
Tool-calling (BFCL single-turn, with stop fix): live_simple ~60 %, live_multiple ~31 %, live_relevance 87.5 %, live_irrelevance ~34 % (over-eager).

Limitations

Repetition loops on OOD multi-turn input (emits the same call many times; avg ~25 calls/turn vs ~1.3 expected). Mitigate with stop=["</tool_call>"] + repeat-penalty.
Over-eager to call tools (does not always decline when it should).
Single-turn exact-match is poor without the stop fix.
~6-pt avg@4 reasoning dip vs base; trained 1 epoch on one dataset config.

Not recommended for production agents as-is.

License

Apache-2.0. Built on WeiboAI/VibeThinker-3B and lambda/hermes-agent-reasoning-traces (both Apache-2.0).

Downloads last month: 452

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

6-bit

8-bit

16-bit

Model tree for RefinedNeuro/VibeThinker-3B-Hermes-GGUF

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-Coder-3B

Finetuned

WeiboAI/VibeThinker-3B

Quantized

(48)

this model

RefinedNeuro
/

VibeThinker-3B-Hermes-GGUF