Instructions to use pointbreaklab/knot-delta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pointbreaklab/knot-delta with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="pointbreaklab/knot-delta",
	filename="kd-delta-9b-Q4_K_M.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 pointbreaklab/knot-delta 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 pointbreaklab/knot-delta:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf pointbreaklab/knot-delta:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf pointbreaklab/knot-delta:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf pointbreaklab/knot-delta: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 pointbreaklab/knot-delta:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf pointbreaklab/knot-delta: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 pointbreaklab/knot-delta:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pointbreaklab/knot-delta:Q4_K_M

Use Docker

docker model run hf.co/pointbreaklab/knot-delta:Q4_K_M

LM Studio
Jan

vLLM

How to use pointbreaklab/knot-delta with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/pointbreaklab/knot-delta:Q4_K_M

Ollama
How to use pointbreaklab/knot-delta with Ollama:
```
ollama run hf.co/pointbreaklab/knot-delta:Q4_K_M
```

Unsloth Studio

How to use pointbreaklab/knot-delta 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 pointbreaklab/knot-delta 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 pointbreaklab/knot-delta to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for pointbreaklab/knot-delta to start chatting

How to use pointbreaklab/knot-delta with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pointbreaklab/knot-delta: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": "pointbreaklab/knot-delta:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use pointbreaklab/knot-delta with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pointbreaklab/knot-delta: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 pointbreaklab/knot-delta:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use pointbreaklab/knot-delta with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pointbreaklab/knot-delta: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 "pointbreaklab/knot-delta: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 pointbreaklab/knot-delta with Docker Model Runner:
```
docker model run hf.co/pointbreaklab/knot-delta:Q4_K_M
```

Lemonade

How to use pointbreaklab/knot-delta with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pointbreaklab/knot-delta:Q4_K_M

Run and chat with the model

lemonade run user.knot-delta-Q4_K_M

List all available models

lemonade list

pointbreaklab commited on 4 days ago

Commit

d6bc4ce

verified ·

1 Parent(s): 2120680

Knot Delta model card

Browse files

Files changed (1) hide show

README.md +77 -0

README.md ADDED Viewed

	@@ -0,0 +1,77 @@

+---
+license: apache-2.0
+base_model: unsloth/Qwen3.5-9B
+pipeline_tag: text-generation
+tags:
+  - code
+  - change-analysis
+  - commit
+  - gguf
+  - on-device
+---
+# Knot Delta
+**On-device model that explains what changed.** Give it a commit and Knot Delta
+writes a grounded report: what moved, why, and the risk. A 9B model, served as a
+single quantized GGUF that runs on your machine.
+Part of the **Knot AI** family, alongside
+[**Knot Scribe**](https://huggingface.co/pointbreaklab/knot-scribe) (which writes
+your commit messages). Delta is the change-intelligence layer inside
+[Knot](https://pointbreaklab.com/knot/).
+A fine-tune of **Qwen3.5-9B**, merged and exported to a text-only
+`Q4_K_M` GGUF (~5.2 GB) for `llama.cpp` / Ollama.
+## Capability scorecard (honest)
+Every number is measured against **objective ground truth** (real git history),
+reported **beside the baseline a lazy model would score**. No aggregate
+"intelligence score" is quoted. Frozen held-out set: **325 commits across 9
+unseen real repos** (vite, vue, svelte, astro, ionic, gumroad, OpenDream,
+radicle, vllm).
+| capability | number | baseline | verdict |
+|---|---|---|---|
+| **Change-type** (intent read from code), macro-F1 | **0.409** | majority-class 0.032 | **real — 12.9× base rate** (n=235) |
+| **Cited files that exist in the diff** | **100%** | — | never hallucinates a file; holds on unseen Go |
+| **Reports fully grounded** | **98.5%** | — | 325 held-out commits (first-pass 88%) |
+| **Exact-line precision** | **0.64** | 0.94 lenient (right region) | honest limit: file + region reliable, exact line ~64% |
+**Multi-repo generalization** (exact-line precision, 4 unseen repos):
+| repo | language | verified | line precision |
+|---|---|---|---|
+| flask | Python | 11/12 | 0.74 |
+| gin | Go (unseen) | 12/12 | 0.70 |
+| ripgrep | Rust | 12/12 | 0.52 |
+| frozen-325 | JS/TS + | 320/325 | 0.64 |
+**Honest read:** Delta never cites a file that isn't in the diff (100% across
+every repo, including Go, which is absent from its training data), and it always
+points at the right region. What it does *not* yet do reliably is pin the exact
+line — that lands 52–74% of the time, lowest on Rust. It knows which file and
+which part changed; the precise line is still improving. One capability,
+measured straight, with the parts that don't yet work said out loud.
+## Use it
+**llama.cpp**
+```bash
+llama-server --model kd-delta-9b-Q4_K_M.gguf
+```
+**Ollama**
+```bash
+ollama run pointbreaklab/knot-delta
+```
+## Model
+- **Base:** Qwen3.5-9B
+- **Format:** text-only `Q4_K_M` GGUF, ~5.2 GB
+- **Runs:** `llama.cpp` / Ollama, CPU or GPU, fully local
+- **License:** Apache-2.0