Instructions to use TendieLabs/Frank-9B-GGUFs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use TendieLabs/Frank-9B-GGUFs 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 TendieLabs/Frank-9B-GGUFs:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TendieLabs/Frank-9B-GGUFs:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TendieLabs/Frank-9B-GGUFs:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TendieLabs/Frank-9B-GGUFs: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 TendieLabs/Frank-9B-GGUFs:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TendieLabs/Frank-9B-GGUFs: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 TendieLabs/Frank-9B-GGUFs:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TendieLabs/Frank-9B-GGUFs:Q4_K_M

Use Docker

docker model run hf.co/TendieLabs/Frank-9B-GGUFs:Q4_K_M

LM Studio
Jan

vLLM

How to use TendieLabs/Frank-9B-GGUFs with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TendieLabs/Frank-9B-GGUFs"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TendieLabs/Frank-9B-GGUFs",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TendieLabs/Frank-9B-GGUFs:Q4_K_M

Ollama
How to use TendieLabs/Frank-9B-GGUFs with Ollama:
```
ollama run hf.co/TendieLabs/Frank-9B-GGUFs:Q4_K_M
```
Unsloth Desktop

How to use TendieLabs/Frank-9B-GGUFs with Pi:

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use TendieLabs/Frank-9B-GGUFs with Docker Model Runner:
```
docker model run hf.co/TendieLabs/Frank-9B-GGUFs:Q4_K_M
```

Lemonade

How to use TendieLabs/Frank-9B-GGUFs with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TendieLabs/Frank-9B-GGUFs:Q4_K_M

Run and chat with the model

lemonade run user.Frank-9B-GGUFs-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use TendieLabs/Frank-9B-GGUFs with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TendieLabs/Frank-9B-GGUFs: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 TendieLabs/Frank-9B-GGUFs:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TendieLabs/Frank-9B-GGUFs with OpenClaw:

Start the llama.cpp server

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

Frank 9B

Frank 9B is a general-purpose LoRA fine-tune of unsloth/Qwen3.5-9B, trained on 17,693 curated examples spanning code review, debugging, reasoning, and creative writing. Designed for fast, capable local inference on consumer GPUs.

Intended Use

Frank 9B is built for local deployment. It targets the sweet spot between size and capability, running comfortably on an RTX 3090 at IQ4_XS quantization (4.9 GB). It handles code review, debugging, structured reasoning, and creative writing with well-formatted, concise responses.

Where the Fred models from TendieLabs specialize in Mermaid diagram generation, Frank 9B is a generalist. The goal is a capable, direct assistant with structured output quality for everyday developer and academic use.

Training

Detail	Value
Base Model	unsloth/Qwen3.5-9B
Method	LoRA (rank 16, alpha 32) via transformers + PEFT
Quantization	8-bit (bitsandbytes) during training
Dataset	17,693 rows (merged multi-source)
Epochs	1
Steps	2,212
Batch Size	1 (gradient accumulation 8)
Max Sequence Length	768
Learning Rate	2e-5 (cosine schedule, 30 warmup steps)
Final Train Loss	0.6828
Training Time	~16 hours on RTX 3090 (24 GB)
Hardware	NVIDIA RTX 3090, CUDA 12.8, Docker container

LoRA target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj

Training Data

The merged dataset combines multiple high-quality sources:

microsoft/rStar-Coder -- Math and code reasoning from competitive programming and STEM problem sets.
NickyNicky/Code-290k -- Multi-language code examples across 15 programming languages.
Crownelius/GLM-5.0-25000x -- General reasoning distillation with thinking traces.
Crownelius/Opus-4.6-Reasoning-3300x -- Claude Opus 4.6 reasoning chains for structured analytical output.
Crownelius/Opus-4.5-Writing-Style-formatted -- Claude writing style and tone.
Crownelius/High-Coder-Reasoning-Multi-Turn -- Multi-turn coding sessions.
Crownelius/Creative-Writing-Sonnet4.6-Cleaned -- Creative writing from Claude Sonnet 4.6.

Eval Results

Compared against the unmodified unsloth/Qwen3.5-9B base model on 5 prompts. Both models were loaded in 8-bit quantization with identical generation parameters (temperature 0.7, top_p 0.9, max 512 tokens). Frank 9B won or tied on every task.

Task	Base Model	Frank 9B	Result
Code Review (Python `merge_counts`)	Catches mutation bug, suggests Counter	Same catches + structured markdown headers, more thorough analysis	Frank wins
Debugging (FastAPI 422 error)	Correct diagnosis, two fix options	Clearer formatting, adds runnable verification code	Frank wins
Explain (Mutex vs Semaphore)	Good comparison table + explanation	Better structure, includes concrete Python code example	Frank wins
General Reasoning (sheep riddle)	Correct but verbose (158 tokens)	Correct and concise (27 tokens)	Frank wins
Creative Code (longest increasing subsequence)	Correct O(n^2) DP implementation	Correct, clean implementation	Tie

Key improvements over the base model:

Better response formatting (markdown headers, tables, structured sections)
More concise where appropriate (no unnecessary verbosity)
Includes practical, runnable code examples in explanations
Same or better correctness across all evaluated tasks

Quantization

An IQ4_XS GGUF quantization is available at 4.9 GB (4.66 bits per weight). IQ4_XS is recommended for MoE and dense models alike as it uses importance-weighted quantization.

Format	Size	BPW
F16 (safetensors)	17 GB	16.0
IQ4_XS (GGUF)	4.9 GB	4.66

Capabilities

Code review with structured, actionable feedback
Debugging diagnosis with working fix examples
Multi-language code generation (Python, JavaScript, Java, Rust, Go, and more)
Mathematical reasoning and step-by-step problem solving
Concise, well-formatted responses with markdown structure
Fast local inference on consumer GPUs

Limitations

Frank 9B is optimized for local consumer hardware use. It is not intended for safety-critical or high-stakes applications. Performance on domains outside the training mix (e.g., medical, legal) has not been evaluated.

Developer

TendieLabs

Downloads last month: 257

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for TendieLabs/Frank-9B-GGUFs

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Adapter

TendieLabs/Frank-9B

Adapter

(3)

this model

TendieLabs
/

Frank-9B-GGUFs

Frank 9B

Intended Use

Training

Training Data

Eval Results

Quantization

Capabilities

Limitations

Developer

Model tree for TendieLabs/Frank-9B-GGUFs

Datasets used to train TendieLabs/Frank-9B-GGUFs