Instructions to use KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-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 KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-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 KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0

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 KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0

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 KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0

Use Docker

docker model run hf.co/KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0

LM Studio
Jan

vLLM

How to use KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-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": "KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0

Ollama
How to use KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF with Ollama:
```
ollama run hf.co/KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0
```
Unsloth Desktop

How to use KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0

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": "KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF with Docker Model Runner:
```
docker model run hf.co/KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0
```

Lemonade

How to use KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0

Run and chat with the model

lemonade run user.Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF-Q4_0

List all available models

lemonade list

Hermes Agent

How to use KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-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 KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0

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 KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0

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 "KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF:Q4_0" \
  --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"

Compact release

A smaller 5.981 GB base + adapter package is available in compact/. The adapter is required. Download only compact/* and follow its loading instructions; downloading this whole repository also fetches the older larger models. The GGUF adapter passed 0/126 refusals and 21/24 benign tasks. MLX has Linux CPU smoke and layer validation, not Apple-hardware validation.

Earlier mixed-precision release

Bonsai 2 27B â€” Philadelphia Class

An abliterated derivative of PrismML Bonsai 2 27B, built with the same two-pass Qwen3.8 Philadelphia recipe. Refusal directions were re-extracted from Bonsai for each pass; no Qwen weights or saved Qwen directions were substituted.

What changed

Two norm-preserving biprojection passes, layers 1â€“63, scale 1.0, 126 output matrices per pass. The 842 paired prompts were split into 716 extraction pairs and 126 family-disjoint held-out pairs with seed 1337. See recipe.json and the two provenance files.

These are mixed-precision models. Unedited quantized language matrices retain their original rotated ternary representation; auxiliary and vision tensors retain their source precision. The 126 edited matrices use canonical, unrotated Q4_0 or Q8_0 values. GDN column ordering and Hadamard manifests were updated accordingly. Pure ternary repacking erased the edit (124/126 held-out refusals), so that failed candidate is not distributed here.

Validation

Model	Refusals / 126	Benign tasks passed / 24
Original Bonsai	123	22
Mixed 4-bit	0	21
Mixed 8-bit	0	21

These are deterministic heuristic screens, not broad intelligence scores. The held-out screen used 96 output tokens, greedy decoding, repetition penalty 1.1, and a 4096-token GGUF context on an A100 80 GB. The intermediate BF16 final checkpoint passed its separate 126-prompt, 24-token opening gate with zero refusals and 100% usable openings. Raw harmful prompts and responses are not included.

MLX checks cover strict full-model reload, one arithmetic generation smoke test on Linux CPU, and independent packed-layer numerical checks. No iPhone, macOS Metal, or App Store validation was performed. Weights need additional runtime and cache memory; file size is not a device RAM requirement. Vision weights are preserved in MLX but vision behavior was not re-evaluated.

Full aggregate results and exact scope are in evaluation.json. Do not apply the upstream model's intelligence or throughput claims to this derivative.

Sources and license

Created using Bonsai by Prism ML. Derived from PrismML GGUF at 6ed5e12bf84b7a63069882c91dd9e9218647d17b and PrismML MLX at 3f926b415992eaa2ae9dd7b573706494d6bbf787. Bonsai derives from Qwen3.8-27B. Weights retain Apache-2.0 licensing; bundled runtime code retains its own MIT license. Modifications made 2026-09-21.

Running GGUF

Requires PrismML's llama.cpp fork; validated revision 9a9394a895b96003ca842a6041cb28ac49a108f7. Stock runtimes that omit the remaining ternary/Hadamard support are incompatible.

File	Decimal GB
`Bonsai-2-27B-Philadelphia-Class-MIXED-PTQ1-Q4_0.gguf`	8.56
`Bonsai-2-27B-Philadelphia-Class-MIXED-PTQ1-Q8_0.gguf`	12.36

hf download KridgeDookie/Ternary-Bonsai-2-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-GGUF Bonsai-2-27B-Philadelphia-Class-MIXED-PTQ1-Q4_0.gguf --local-dir bonsai
./llama.cpp/build/bin/llama-server -m bonsai/Bonsai-2-27B-Philadelphia-Class-MIXED-PTQ1-Q4_0.gguf -ngl 99 -c 4096

The optional original GGUF vision projector is available in the upstream PrismML repository; it is not bundled or revalidated here.