Instructions to use Ttimms/KAT-Coder-V2.5-Dev-REAP-50-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 Ttimms/KAT-Coder-V2.5-Dev-REAP-50-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 Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF: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 Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF: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 Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ttimms/KAT-Coder-V2.5-Dev-REAP-50-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": "Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF:Q4_K_M

Ollama
How to use Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF with Ollama:
```
ollama run hf.co/Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF: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": "Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF with Docker Model Runner:
```
docker model run hf.co/Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF:Q4_K_M
```

Lemonade

How to use Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.KAT-Coder-V2.5-Dev-REAP-50-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Ttimms/KAT-Coder-V2.5-Dev-REAP-50-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 Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF: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 Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF: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 "Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF: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 · REAP-50 — GGUF

GGUF quants of the 50%-REAP-pruned KAT-Coder-V2.5-Dev (Gated-DeltaNet + MoE hybrid): 256 → 128 experts, ~17.5B parameters, no MTP head.

Flagship (NVFP4A16, vLLM): Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16
Pruned bf16 source: Ttimms/KAT-Coder-V2.5-Dev-REAP-50-bf16
Pipeline + benchmarks: https://github.com/t-timms/kat-coder-16gb

Base-model quality (NVFP4A16 quant, greedy, instruct): HumanEval+ ~90%, MBPP+ ~90%.

Quants

File	Quant	Size	Notes
`kat-reap50-Q4_K_M.gguf`	Q4_K_M	~11 GB	recommended — fits a 16 GB card with room for context
`kat-reap50-Q5_K_M.gguf`	Q5_K_M	~13 GB
`kat-reap50-Q6_K.gguf`	Q6_K	~15 GB
`kat-reap50-Q8_0.gguf`	Q8_0	~19 GB	near-lossless; needs CPU offload or >16 GB

For full precision, re-quantizing, or merging, use the pruned bf16 source and run convert_hf_to_gguf.py --no-mtp yourself.

MoE with ~3B active parameters — CPU and Apple-Silicon inference is fast for the size.

Requirements

Needs a recent llama.cpp (the qwen3_5_moe hybrid arch). Verified with llama-server from a source build. Ollama support pending its bundled-llama.cpp bump.

llama-server -m kat-reap50-Q4_K_M.gguf -ngl 99 --port 8080

The chat template defaults to thinking on; pass "chat_template_kwargs": {"enable_thinking": false} for direct output.

License

Apache-2.0 (inherits from Kwaipilot/KAT-Coder-V2.5-Dev). Pruning: REAP (github.com/CerebrasResearch/reap, with a router-renormalization fix).

Downloads last month: 21

GGUF

Model size

19B params

Architecture

qwen35moe

Hardware compatibility

4-bit

5-bit

6-bit

8-bit