Instructions to use KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS")
model = AutoModelForMultimodalLM.from_pretrained("KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS 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/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS: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 KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS: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 KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS:Q4_K_M

Use Docker

docker model run hf.co/KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS:Q4_K_M

LM Studio
Jan

vLLM

How to use KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS"
# 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/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS:Q4_K_M

SGLang

How to use KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS with Ollama:
```
ollama run hf.co/KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS:Q4_K_M
```

Unsloth Studio

How to use KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS 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 KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS 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 KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS to start chatting

How to use KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS: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": "KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS with Docker Model Runner:
```
docker model run hf.co/KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS:Q4_K_M
```

Lemonade

How to use KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS:Q4_K_M

Run and chat with the model

lemonade run user.KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS 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/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS: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 KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS: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 "KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS: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"

KAT-Coder V2.5 Dev 35B-A3B - ABLITERATED UNCENSORED PHILADELPHIA CLASS

0 hard refusals across 842 internal test prompts, 0 hard refusals across a separate 126-prompt holdout, and 23/24 coherence checks passed.

These are internal evaluation results, not third-party benchmarks, and may not generalize to every prompt or use case.

PHILADELPHIA CLASS is a text-only 35B-total/3B-active MoE derivative of Kwaipilot/KAT-Coder-V2.5-Dev. It is modified to reduce refusal behavior while retaining the upstream checkpoint format and coding-oriented architecture. The release includes the full BF16 checkpoint plus Q4_K_M, Q5_K_M, and Q8_0 GGUF options.

Standout results

Evaluation	Result
842-prompt refusal test	0 hard refusals, 6 soft-prefaced responses, 99.29% usable
Separate 126-prompt holdout	0 hard refusals, 5 soft-prefaced responses, 95.24% usable
24-task coherence check	23/24 passed

Created with targeted post-training weight editing to reduce refusal behavior while preserving the parent model's coding capabilities.

Model details

Direct parent: Kwaipilot/KAT-Coder-V2.5-Dev
Architecture: Mixture of Experts, 35B total parameters and approximately 3B active parameters
Precision: BF16 original; Q4_K_M, Q5_K_M, and Q8_0 GGUF quantizations
Modality: text only
Focus: coding and agentic coding workflows
Weight format: one model.safetensors file (unsharded); each GGUF quantization is also a single file
License: Apache 2.0, inherited from the direct parent

The upstream open-weight release contains language-model weights only. It does not include a vision tower.

Transformers usage

The checkpoint was loaded and evaluated with Transformers 5.14.1 on an NVIDIA RTX PRO 6000 Blackwell Server Edition GPU.

pip install "transformers[serving]==5.14.1" accelerate
transformers serve KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS --port 8000

The server exposes an OpenAI-compatible API at http://localhost:8000/v1.

vLLM usage

KAT-Coder's open checkpoint is text-only, so --language-model-only is required to prevent the runtime from attempting to initialize unavailable vision weights.

pip install "vllm>=0.19.0"
vllm serve KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS \
  --port 8000 \
  --max-model-len 32768 \
  --reasoning-parser qwen3 \
  --language-model-only

The full BF16 checkpoint is roughly 65 GiB. Although only about 3B parameters are active for each token, the complete MoE checkpoint still needs to be loaded, so practical memory requirements are much higher than those of a dense 3B model. Longer context lengths require additional memory.

GGUF downloads

File	Approximate size	Suggested use
`Q4_K_M-KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS.gguf`	21 GB	Best general size/quality balance
`Q5_K_M-KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS.gguf`	25 GB	More quality with moderate extra memory
`Q8_0-KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS.gguf`	37 GB	Highest-fidelity quantized option

Download one quantization with the current Hugging Face CLI:

hf download KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS \
  --include "Q4_K_M-*.gguf" \
  --local-dir .

Run it with llama.cpp:

llama-cli \
  -m ./Q4_K_M-KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS.gguf \
  -ngl 99 \
  -c 32768 \
  --jinja

Or import the same file into Ollama:

FROM ./Q4_K_M-KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS.gguf
PARAMETER num_ctx 32768

Save that as Modelfile, then run ollama create kat-coder-philadelphia -f Modelfile.

Limitations

Refusal reduction does not guarantee better coding ability, factual accuracy, judgment, or tool use.
The reported results are based on internal evaluations and have not been independently audited.
This release is text-only and cannot accept image or video inputs.
The model can generate incorrect, insecure, or otherwise harmful output. Review generated code before using it.

Attribution

This model is derived from Kwaipilot/KAT-Coder-V2.5-Dev, which in turn builds on the Qwen3.6-35B-A3B family. Please retain the upstream attribution and follow the Apache 2.0 license.

Downloads last month: 16,998

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS

Base model

Kwaipilot/KAT-Coder-V2.5-Dev

Quantized

(66)

this model

Quantizations

1 model