Instructions to use moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16 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 moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16
# Run inference directly in the terminal:
llama cli -hf moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16
# Run inference directly in the terminal:
llama cli -hf moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16

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 moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16
# Run inference directly in the terminal:
./llama-cli -hf moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16

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 moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16

Use Docker

docker model run hf.co/moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16

LM Studio
Jan

vLLM

How to use moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16

Ollama
How to use moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16 with Ollama:
```
ollama run hf.co/moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16
```
Unsloth Desktop

How to use moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16

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": "moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16 with Docker Model Runner:
```
docker model run hf.co/moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16
```

Lemonade

How to use moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16

Run and chat with the model

lemonade run user.KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16-BF16

List all available models

lemonade list

Hermes Agent

How to use moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16

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 moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16

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 "moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16:BF16" \
  --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-MTP-BF16

Full-precision single-file GGUF (BF16) of the abliterated KAT-Coder V2.5 Dev 35B-A3B, with the fine-tuned Qwen3.6-35B-A3B MTP (multi-token prediction) head embedded in the model for speculative decoding.

Trunk: KridgeDookie's abliterated KAT-Coder V2.5 Dev 35B-A3B ("PHILADELPHIA CLASS", refusal-reduced)
MTP head: original-mtp-head.safetensors from gbuzhf/KAT-Coder-V2.5-Dev-MTP-GGUF (byte-identical to the Qwen/Qwen3.6-35B-A3B donor head at build time)
Format: GGUF v3, full BF16 (general.file_type = 32, MOSTLY_BF16; small 1-D tensors are F32, as standard)

File

File	Size	Type
`KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16.gguf`	71.1 GB (66.2 GiB)	GGUF v3, BF16, single file

No split parts needed — the file downloads and runs directly.

Model details

Verified from the GGUF header:

Property	Value
Architecture	`qwen35moe` (Qwen3.6-35B-A3B class, hybrid SSM + full attention every 4 layers)
Parameters	35B total / ~3B active per token
Experts	256, 8 active (shared expert included)
Layers	41 (`block_count = 41`)
Context length	262,144 tokens
Hidden size	2,048
Tensors	753
MTP	`nextn_predict_layers = 1` (embedded)

Usage (llama.cpp)

llama-cli -m KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16.gguf \
  -p "Hello" -n 64 --spec-type draft-mtp

(Exact MTP flag name depends on your llama.cpp build; recent builds expose it as --spec-type draft-mtp.)

Hardware note

BF16 full precision: the weights alone are ~66 GiB, so plan for roughly 75+ GB of free RAM/VRAM (CPU offload works, but expect slow prompt and decode speeds). For lower resource requirements, use a quantized build — the parent repo KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS ships Q4_K_M, Q5_K_M, and Q8_0 GGUF options.

Provenance

Part	Source
Abliterated trunk	KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS
MTP head	gbuzhf/KAT-Coder-V2.5-Dev-MTP-GGUF (`original-mtp-head.safetensors`)
Conversion	llama.cpp `convert_hf_to_gguf.py` (bf16, full export)

License

Apache 2.0, inherited from the parent model.

Downloads last month: 272

GGUF

Model size

36B params

Architecture

qwen35moe

Hardware compatibility

16-bit

Model tree for moeshawky/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-MTP-BF16

Base model

Kwaipilot/KAT-Coder-V2.5-Dev

Quantized

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

Quantized

(1)

this model