Instructions to use devshub-ai/knack with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use devshub-ai/knack 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 devshub-ai/knack:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf devshub-ai/knack:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/devshub-ai/knack:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use devshub-ai/knack with Ollama:
```
ollama run hf.co/devshub-ai/knack:Q4_K_M
```
Unsloth Desktop

How to use devshub-ai/knack with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf devshub-ai/knack: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": "devshub-ai/knack:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use devshub-ai/knack with Docker Model Runner:
```
docker model run hf.co/devshub-ai/knack:Q4_K_M
```

Lemonade

How to use devshub-ai/knack with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull devshub-ai/knack:Q4_K_M

Run and chat with the model

lemonade run user.knack-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use devshub-ai/knack with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf devshub-ai/knack: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 devshub-ai/knack:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use devshub-ai/knack with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf devshub-ai/knack: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 "devshub-ai/knack: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"

mmoussa commited on about 9 hours ago

Commit

dfaba4c

verified ·

1 Parent(s): 9acb30c

Correct Ollama sizes

Browse files

Files changed (2) hide show

README.md +3 -3
knack.py +2 -2

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ in about 10 milliseconds.
 - **Free.** Ships with every CodeSync install. No API key, no account, no usage limits.
 - **Private.** Runs locally. Your prompts and commands never leave your machine to be judged.
 - **Fast.** About 10 ms per decision on a GPU, about 250 ms on a plain CPU.
-- **Small.** 0.5B parameters. 546 MB (Q8_0) or 371 MB (Q4_K_M) in Ollama.
 - **Accurate where it matters.** Trained on real CodeSync sessions, with extra focus on the
   rare cases that cost the most when missed: destructive deletes, commands that never exit,
   resuming interrupted work, refactor / test / documentation requests.
@@ -65,8 +65,8 @@ python3 knack.py serve --port 33727                    # POST /v1/systemone (Cod
 ## Use it with Ollama directly
 ```bash
-ollama pull devshub/knack              # Q8_0, 546 MB  (https://ollama.com/devshub/knack)
-ollama pull devshub/knack:q4_k_m       # 371 MB, near-identical accuracy
 ollama pull hf.co/devshub-ai/knack:Q8_0   # same model, straight from this repo
 ```

 - **Free.** Ships with every CodeSync install. No API key, no account, no usage limits.
 - **Private.** Runs locally. Your prompts and commands never leave your machine to be judged.
 - **Fast.** About 10 ms per decision on a GPU, about 250 ms on a plain CPU.
+- **Small.** 0.75B parameters in the Ollama edition: 817 MB (Q8_0) or 516 MB (Q4_K_M).
 - **Accurate where it matters.** Trained on real CodeSync sessions, with extra focus on the
   rare cases that cost the most when missed: destructive deletes, commands that never exit,
   resuming interrupted work, refactor / test / documentation requests.
 ## Use it with Ollama directly
 ```bash
+ollama pull devshub/knack              # Q8_0, 817 MB  (https://ollama.com/devshub/knack)
+ollama pull devshub/knack:q4_k_m       # 516 MB, near-identical accuracy
 ollama pull hf.co/devshub-ai/knack:Q8_0   # same model, straight from this repo
 ```

knack.py CHANGED Viewed

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 """CodeSync Knack, standalone: ask the model CodeSync's judgment questions through Ollama.
-Standard library only. Needs Ollama (https://ollama.com) running; the model (546 MB) is
 pulled on first use. One-liner, nothing to install:
     curl -fsSL https://huggingface.co/devshub-ai/knack/resolve/main/knack.py | python3 - "rm -rf build/"
@@ -20,7 +20,7 @@ answer is the most likely of THOSE letters, renormalised (this script does that
 Ollama's logprobs). Do not read the raw generated letter on its own.
 Env: KNACK_OLLAMA_HOST (default http://127.0.0.1:11434),
-     KNACK_MODEL (default devshub/knack; devshub/knack:q4_k_m is smaller, 371 MB;
      hf.co/devshub-ai/knack:Q8_0 pulls the same model from Hugging Face).
 """

 #!/usr/bin/env python3
 """CodeSync Knack, standalone: ask the model CodeSync's judgment questions through Ollama.
+Standard library only. Needs Ollama (https://ollama.com) running; the model (817 MB) is
 pulled on first use. One-liner, nothing to install:
     curl -fsSL https://huggingface.co/devshub-ai/knack/resolve/main/knack.py | python3 - "rm -rf build/"
 Ollama's logprobs). Do not read the raw generated letter on its own.
 Env: KNACK_OLLAMA_HOST (default http://127.0.0.1:11434),
+     KNACK_MODEL (default devshub/knack; devshub/knack:q4_k_m is smaller, 516 MB;
      hf.co/devshub-ai/knack:Q8_0 pulls the same model from Hugging Face).
 """