Instructions to use rrchat/Viper-9B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use rrchat/Viper-9B-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 rrchat/Viper-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rrchat/Viper-9B-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 rrchat/Viper-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rrchat/Viper-9B-GGUF:Q4_K_M

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 rrchat/Viper-9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf rrchat/Viper-9B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/rrchat/Viper-9B-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use rrchat/Viper-9B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rrchat/Viper-9B-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": "rrchat/Viper-9B-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/rrchat/Viper-9B-GGUF:Q4_K_M

Ollama
How to use rrchat/Viper-9B-GGUF with Ollama:
```
ollama run hf.co/rrchat/Viper-9B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use rrchat/Viper-9B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rrchat/Viper-9B-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": "rrchat/Viper-9B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use rrchat/Viper-9B-GGUF with Docker Model Runner:
```
docker model run hf.co/rrchat/Viper-9B-GGUF:Q4_K_M
```

Lemonade

How to use rrchat/Viper-9B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rrchat/Viper-9B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Viper-9B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use rrchat/Viper-9B-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 rrchat/Viper-9B-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 rrchat/Viper-9B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use rrchat/Viper-9B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rrchat/Viper-9B-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 "rrchat/Viper-9B-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"

Viper-9B-GGUF

Official quantized GGUF release for rrchat/Viper-9B, the flagship conversational, coding, and agentic language model of the RR-Gen1 lineup developed by rrchat (huggingface.co/rrchat), fine-tuned on top of Qwen3.5-9B.

Looking for the full unquantized weights (safetensors / PyTorch)?
👉 rrchat/Viper-9B

📦 Available Files & Quantizations

All GGUF quants were prepared using llama.cpp with domain-specific importance matrix calibration (imatrix):

File	Size	VRAM Req.	Recommended Use Case
`Viper-9B-Q4_K_M.gguf`	5.63 GB	~8 GB	Efficient inference on 8 GB GPUs and edge systems
`Viper-9B-Q5_K_M.gguf`	6.47 GB	~10–12 GB	Primary recommended quant (Optimal balance of speed, accuracy, and full context)
`Viper-9B-Q6_K.gguf`	7.36 GB	~12–16 GB	High-precision workstation inference
`Viper-9B-Q8_0.gguf`	9.53 GB	~16 GB+	Near-lossless 16-bit reference quality
`mmproj-Viper-9B-f16.gguf`	918 MB	~1 GB	Multimodal vision projector (Standard FP16)
`mmproj-Viper-9B-BF16.gguf`	922 MB	~1 GB	Multimodal vision projector (Native BF16)
`Viper-9B.imatrix`	5.15 MB	—	Domain-specific importance matrix calibration data

🧪 Benchmark Highlights (vs. Base Model)

All benchmarks were evaluated locally on an identical test harness under strictly identical conditions:

Benchmark	Mode / Harness	Base (`Qwen3.5-9B`)	Viper-9B	Delta vs. Base	Domain / Capability
LiveCodeBench v6	Deterministic Pass@1	19.0%	33.0%	+14.0%	Competitive programming & algorithmic tasks
↳ LCB v6 Easy	Deterministic Pass@1	42.4%	60.6%	+18.2%	Standard algorithmic challenges
↳ LCB v6 Medium	Deterministic Pass@1	14.7%	29.4%	+14.7%	Complex dynamic programming & data structures
↳ LCB v6 Hard	Deterministic Pass@1	0.0%	9.1%	+9.1%	Advanced competitive problem solving
MBPP+ (seed 42)	EvalPlus Pass@1	83.3%	84.7%	+1.4%	Python function synthesis & unit tests
MGSM ru (Math)	Numeric Match	42.0%	44.4%	+2.4%	Russian multi-step mathematical reasoning
MMLU-Redux	Choice Accuracy	73.7%	74.0%	+0.3%	Broad multidisciplinary STEM & humanities
BFCL v4 (Tool Use)	AST Function Match	58.0%	57.0%	Parity (~57%)	Berkeley Function Calling / Agentic Tool Calls
IFEval (Instruction)	Strict Compliance	56.6%	54.7%	Parity (~55%)	Complex constraint & prompt compliance

Disclaimer on Evaluations:
All benchmarks presented above were conducted manually and independently on local test suites under controlled, strictly identical conditions (greedy non-thinking mode, max_tokens 1024, llama-server with jinja chat formatting). The results reflect real-world local execution performance and may differ from theoretical, thinking-mode, or officially reported figures published on the official base model card.

🚀 How to Run

1. In Ollama

Create a model using the provided Modelfile:

ollama create Viper-9B -f Modelfile
ollama run Viper-9B "Привет! Расскажи о себе."

Or for instant non-thinking responses:

ollama create Viper-9B-fast -f Modelfile.fast

2. In llama.cpp CLI

llama-cli.exe \
  -m Viper-9B-Q5_K_M.gguf \
  --mmproj mmproj-Viper-9B-f16.gguf \
  -p "<|im_start|>user\nПривет! Кто ты?<|im_end|>\n<|im_start|>assistant\n" \
  -ngl 99 \
  -c 8192 \
  --temp 0.7

3. In llama-server (OpenAI-Compatible API)

llama-server.exe \
  -m Viper-9B-Q5_K_M.gguf \
  --mmproj mmproj-Viper-9B-f16.gguf \
  -ngl 99 \
  -c 8192 \
  --port 8080 \
  --host 127.0.0.1

Downloads last month: -

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Model tree for rrchat/Viper-9B-GGUF

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(644)

this model

Collection including rrchat/Viper-9B-GGUF

RR-Gen1

Collection

Our first generation of open-weight models • 8 items • Updated about 12 hours ago • 1