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

Use Docker

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

LM Studio
Jan

vLLM

How to use RemySkye/KAT-Coder-V2.5-Dev-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

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

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

How to use RemySkye/KAT-Coder-V2.5-Dev-GGUF with Pi:

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use RemySkye/KAT-Coder-V2.5-Dev-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Hermes Agent

How to use RemySkye/KAT-Coder-V2.5-Dev-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 RemySkye/KAT-Coder-V2.5-Dev-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 RemySkye/KAT-Coder-V2.5-Dev-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use RemySkye/KAT-Coder-V2.5-Dev-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RemySkye/KAT-Coder-V2.5-Dev-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 "RemySkye/KAT-Coder-V2.5-Dev-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-GGUF / build-manifest.json

RemySkye

Update GGUF build manifest

ab133d9 verified about 2 months ago

Raw

History Blame

7.2 kB

	{
	"base_model": "Kwaipilot/KAT-Coder-V2.5-Dev",
	"created_at": "2026-07-23T19:55:11.780924+00:00",
	"files": {
	"KAT-Coder-V2.5-Dev-BF16.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "BF16",
	"sha256": "f15114d487105dafc8deb7b77b84220c7b47cb87155cd83d684b2eb794f4ef92",
	"size_bytes": 69376637376,
	"tensor_count": 733,
	"tensor_types": {
	"BF16": 432,
	"F32": 301
	},
	"verified_remote_size": 69376637376
	},
	"KAT-Coder-V2.5-Dev-IQ4_XS.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "IQ4_XS",
	"sha256": "7edb4250dcabcaa25c03f09baa738d4433e92a1f7886333339839fa472bc579b",
	"size_bytes": 18939312256,
	"tensor_count": 733,
	"tensor_types": {
	"F32": 301,
	"IQ4_XS": 381,
	"Q5_K": 50,
	"Q6_K": 1
	},
	"verified_remote_size": 18939312256
	},
	"KAT-Coder-V2.5-Dev-Q2_K.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "Q2_K",
	"sha256": "3541c65e3c40c6759db99fea59d9ced00d96bf7d488966d15e332baa9fbe90e6",
	"size_bytes": 12939593856,
	"tensor_count": 733,
	"tensor_types": {
	"F32": 301,
	"Q2_K": 301,
	"Q3_K": 90,
	"Q4_K": 40,
	"Q6_K": 1
	},
	"verified_remote_size": 12939593856
	},
	"KAT-Coder-V2.5-Dev-Q3_K_L.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "Q3_K_L",
	"sha256": "8d878345b2dc63a364b3f5ee7c883ea51dc97aee09265a6664cc5bd300c133bd",
	"size_bytes": 18115330176,
	"tensor_count": 733,
	"tensor_types": {
	"F32": 301,
	"Q3_K": 301,
	"Q5_K": 130,
	"Q6_K": 1
	},
	"verified_remote_size": 18115330176
	},
	"KAT-Coder-V2.5-Dev-Q3_K_M.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "Q3_K_M",
	"sha256": "a7c85950a7b3317cfec1d89aa09d22cca7e8bbe3b1bcddf7d87b194a56cfa6cd",
	"size_bytes": 16764764288,
	"tensor_count": 733,
	"tensor_types": {
	"F32": 301,
	"Q3_K": 301,
	"Q4_K": 124,
	"Q5_K": 6,
	"Q6_K": 1
	},
	"verified_remote_size": 16764764288
	},
	"KAT-Coder-V2.5-Dev-Q3_K_S.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "Q3_K_S",
	"sha256": "5842118485db74051bcfd845789b223a2f7cefea686e42fca3b16b4780f9fcbc",
	"size_bytes": 15182184576,
	"tensor_count": 733,
	"tensor_types": {
	"F32": 301,
	"Q3_K": 431,
	"Q6_K": 1
	},
	"verified_remote_size": 15182184576
	},
	"KAT-Coder-V2.5-Dev-Q4_0.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "Q4_0",
	"sha256": "2164de0b1e9c78354516a9b641abbad7d5aa76c408b7ead6c8a0bc990d4c439e",
	"size_bytes": 19715053696,
	"tensor_count": 733,
	"tensor_types": {
	"F32": 301,
	"Q4_0": 431,
	"Q6_K": 1
	},
	"verified_remote_size": 19715053696
	},
	"KAT-Coder-V2.5-Dev-Q4_1.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "Q4_1",
	"sha256": "c0dbc5d934e0a73f6d57bb5d14b46f74dcd3fc7c795d2032e786d7955251c8ed",
	"size_bytes": 21848168576,
	"tensor_count": 733,
	"tensor_types": {
	"F32": 301,
	"Q4_1": 431,
	"Q6_K": 1
	},
	"verified_remote_size": 21848168576
	},
	"KAT-Coder-V2.5-Dev-Q4_K_M.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "Q4_K_M",
	"sha256": "51f783d1f9d09234ab5336611fa89ec4c9853520f917ffa00ac290db9c1e4fba",
	"size_bytes": 21166758016,
	"tensor_count": 733,
	"tensor_types": {
	"F32": 301,
	"Q4_K": 371,
	"Q6_K": 61
	},
	"verified_remote_size": 21166758016
	},
	"KAT-Coder-V2.5-Dev-Q4_K_S.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "Q4_K_S",
	"sha256": "3bc4a3b089af9d59e1d522e448ece19478d5f24b288cddb819562fe2c8cbf56a",
	"size_bytes": 19889903744,
	"tensor_count": 733,
	"tensor_types": {
	"F32": 301,
	"Q4_K": 417,
	"Q5_K": 14,
	"Q6_K": 1
	},
	"verified_remote_size": 19889903744
	},
	"KAT-Coder-V2.5-Dev-Q5_0.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "Q5_0",
	"sha256": "976b7bd374b322bf07bb3f5103e1cdd9ace09c07b8ca1b50d7b9a9fbdc64cfb9",
	"size_bytes": 23981283456,
	"tensor_count": 733,
	"tensor_types": {
	"F32": 301,
	"Q5_0": 431,
	"Q6_K": 1
	},
	"verified_remote_size": 23981283456
	},
	"KAT-Coder-V2.5-Dev-Q5_1.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "Q5_1",
	"sha256": "f9112416a9b915a63ee174765e17e271681dc77f3e256a27414862e746f4b594",
	"size_bytes": 26114398336,
	"tensor_count": 733,
	"tensor_types": {
	"F32": 301,
	"Q5_1": 431,
	"Q6_K": 1
	},
	"verified_remote_size": 26114398336
	},
	"KAT-Coder-V2.5-Dev-Q5_K_M.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "Q5_K_M",
	"sha256": "ac503cac28c4bb940d7b3fbf4ff5a2d8de3e4e7331746f5074390eb593ff3853",
	"size_bytes": 24729131136,
	"tensor_count": 733,
	"tensor_types": {
	"F32": 301,
	"Q5_K": 371,
	"Q6_K": 61
	},
	"verified_remote_size": 24729131136
	},
	"KAT-Coder-V2.5-Dev-Q5_K_S.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "Q5_K_S",
	"sha256": "cfe0c7e7c3017c5183d91ec41a17270938783720f72280e456b388914f3f2c7e",
	"size_bytes": 23981283456,
	"tensor_count": 733,
	"tensor_types": {
	"F32": 301,
	"Q5_K": 431,
	"Q6_K": 1
	},
	"verified_remote_size": 23981283456
	},
	"KAT-Coder-V2.5-Dev-Q6_K.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "Q6_K",
	"sha256": "aa8930bdac77ae35c0cff4f5efc5a803fb70ab969dc69eaafa444689e9e791a8",
	"size_bytes": 28514152576,
	"tensor_count": 733,
	"tensor_types": {
	"F32": 301,
	"Q6_K": 432
	},
	"verified_remote_size": 28514152576
	},
	"KAT-Coder-V2.5-Dev-Q8_0.gguf": {
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"quantization": "Q8_0",
	"sha256": "9147989a5946aae624727fdc222019c9828456b61b4adbd451bf80a54a3718bf",
	"size_bytes": 36903139456,
	"tensor_count": 733,
	"tensor_types": {
	"F32": 301,
	"Q8_0": 432
	},
	"verified_remote_size": 36903139456
	}
	},
	"llama_cpp_commit": "c0bc8591e8815c63cb01dd3f051a8b0df02501c9",
	"schema_version": 1,
	"target_repo": "RemySkye/KAT-Coder-V2.5-Dev-GGUF",
	"updated_at": "2026-07-23T21:06:25.019461+00:00"
	}