Instructions to use zaindanaharper/flywheel-local-coder-14b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use zaindanaharper/flywheel-local-coder-14b 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 zaindanaharper/flywheel-local-coder-14b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zaindanaharper/flywheel-local-coder-14b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf zaindanaharper/flywheel-local-coder-14b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf zaindanaharper/flywheel-local-coder-14b: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 zaindanaharper/flywheel-local-coder-14b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf zaindanaharper/flywheel-local-coder-14b: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 zaindanaharper/flywheel-local-coder-14b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf zaindanaharper/flywheel-local-coder-14b:Q4_K_M

Use Docker

docker model run hf.co/zaindanaharper/flywheel-local-coder-14b:Q4_K_M

LM Studio
Jan

vLLM

How to use zaindanaharper/flywheel-local-coder-14b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zaindanaharper/flywheel-local-coder-14b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zaindanaharper/flywheel-local-coder-14b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zaindanaharper/flywheel-local-coder-14b:Q4_K_M

Ollama
How to use zaindanaharper/flywheel-local-coder-14b with Ollama:
```
ollama run hf.co/zaindanaharper/flywheel-local-coder-14b:Q4_K_M
```

Unsloth Studio

How to use zaindanaharper/flywheel-local-coder-14b 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 zaindanaharper/flywheel-local-coder-14b 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 zaindanaharper/flywheel-local-coder-14b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for zaindanaharper/flywheel-local-coder-14b to start chatting

How to use zaindanaharper/flywheel-local-coder-14b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zaindanaharper/flywheel-local-coder-14b:Q4_K_M

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": "zaindanaharper/flywheel-local-coder-14b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use zaindanaharper/flywheel-local-coder-14b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zaindanaharper/flywheel-local-coder-14b: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 zaindanaharper/flywheel-local-coder-14b:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use zaindanaharper/flywheel-local-coder-14b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf zaindanaharper/flywheel-local-coder-14b: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 "zaindanaharper/flywheel-local-coder-14b: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"

Docker Model Runner
How to use zaindanaharper/flywheel-local-coder-14b with Docker Model Runner:
```
docker model run hf.co/zaindanaharper/flywheel-local-coder-14b:Q4_K_M
```

Lemonade

How to use zaindanaharper/flywheel-local-coder-14b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull zaindanaharper/flywheel-local-coder-14b:Q4_K_M

Run and chat with the model

lemonade run user.flywheel-local-coder-14b-Q4_K_M

List all available models

lemonade list

flywheel-local-coder-14b / SPECS.md

papacr0w

Ship user-facing docs: model card, benchmarks with evidence, spec sheet, portable usage and safety pages

a0101b6 verified 24 days ago

preview code

Raw

History Blame Contribute Delete

2.43 kB

	# Spec Sheet

	## The model

	\| \| \|
	\|---\|---\|
	\| Name \| Flywheel-Local-Coder-14B \|
	\| Architecture \| qwen2 (transformer, decoder-only) \|
	\| Parameters \| 14.8B \|
	\| Context length \| 32,768 tokens \|
	\| Embedding size \| 5,120 \|
	\| Capabilities \| chat, code completion, tool calling \|
	\| Base model \| Qwen/Qwen2.5-Coder-14B-Instruct \|
	\| License \| Apache-2.0 with Qwen attribution \|

	## The file

	\| \| \|
	\|---\|---\|
	\| Format \| GGUF, single file \|
	\| Quantization \| Q4_K_M \|
	\| Size \| 8.99 GB (8,988,110,880 bytes) \|
	\| SHA-256 \| `613db240e3efc6730f24042a4602d1f12f1c6b397af1d5a4d74f4e064d4064be` \|
	\| Verify \| `sha256sum telos-coder-14b-cpt2020-q4_k_m.gguf` and compare with [checksums.sha256](checksums.sha256) \|

	## Hardware guidance

	- GPU: fits fully on a 24 GB card with room for context. Smaller cards work
	with partial CPU offload; expect lower speed.
	- CPU only: works. Budget roughly 12 GB of free RAM for the weights plus
	context; generation is slower but entirely usable for chat and completion.
	- Disk: 9 GB for the file itself.

	Runs anywhere llama.cpp or Ollama runs: Windows, Linux, macOS.

	## How it was trained

	Continued pretraining (QLoRA) of the base model on a 66.2-million-token corpus
	of 17,997 files from a real, working development ecosystem: production code,
	tests, documentation, and research notes. Training ran to adapter checkpoint
	2020 (final train loss 0.035), the adapter was merged into the base weights,
	and the merge was quantized to Q4_K_M.

	Every layer of that build is hashed and recorded in
	[provenance.json](provenance.json): the corpus content, the packed training
	shards, the adapter checkpoint, and the final GGUF. Given the same inputs, an
	outside observer can re-derive and verify each link of the chain.

	The training corpus is proprietary and is not distributed with the model.

	## What this model is for

	A local-first coding companion: code completion, small functions, refactors,
	test writing, and tool-calling workflows where your code must not leave your
	machine. It pairs naturally with a verification loop (propose, test, accept
	only what passes), which is exactly how we benchmark it.

	## Known boundaries

	- No claimed capability uplift over the base model; see [BENCHMARKS.md](BENCHMARKS.md).
	- No public leaderboard scores yet.
	- Knowledge cutoff and multilingual behavior follow the base model.
	- A 32B sibling is planned but not yet trained; nothing is published for it.