Instructions to use NANI-Nithin/K2-Horizon-0.9B-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 NANI-Nithin/K2-Horizon-0.9B-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 NANI-Nithin/K2-Horizon-0.9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NANI-Nithin/K2-Horizon-0.9B-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 NANI-Nithin/K2-Horizon-0.9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NANI-Nithin/K2-Horizon-0.9B-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 NANI-Nithin/K2-Horizon-0.9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NANI-Nithin/K2-Horizon-0.9B-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 NANI-Nithin/K2-Horizon-0.9B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NANI-Nithin/K2-Horizon-0.9B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/NANI-Nithin/K2-Horizon-0.9B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use NANI-Nithin/K2-Horizon-0.9B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NANI-Nithin/K2-Horizon-0.9B-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": "NANI-Nithin/K2-Horizon-0.9B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NANI-Nithin/K2-Horizon-0.9B-GGUF:Q4_K_M

Ollama
How to use NANI-Nithin/K2-Horizon-0.9B-GGUF with Ollama:
```
ollama run hf.co/NANI-Nithin/K2-Horizon-0.9B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use NANI-Nithin/K2-Horizon-0.9B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NANI-Nithin/K2-Horizon-0.9B-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": "NANI-Nithin/K2-Horizon-0.9B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use NANI-Nithin/K2-Horizon-0.9B-GGUF with Docker Model Runner:
```
docker model run hf.co/NANI-Nithin/K2-Horizon-0.9B-GGUF:Q4_K_M
```

Lemonade

How to use NANI-Nithin/K2-Horizon-0.9B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NANI-Nithin/K2-Horizon-0.9B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.K2-Horizon-0.9B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use NANI-Nithin/K2-Horizon-0.9B-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 NANI-Nithin/K2-Horizon-0.9B-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 NANI-Nithin/K2-Horizon-0.9B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use NANI-Nithin/K2-Horizon-0.9B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NANI-Nithin/K2-Horizon-0.9B-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 "NANI-Nithin/K2-Horizon-0.9B-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"

K2-Horizon-0.9B — GGUF Quantizations

GGUF quantizations of IFM/K2-Horizon-0.9B, a dense 0.9B-parameter causal decoder (K2HorizonForCausalLM, model_type: k2_horizon).

Quantized by NANI-Nithin using a custom pipeline built on the MBZUAI-IFM llama.cpp fork (branch model/K2Horizon), which adds native support for the k2-horizon architecture not yet merged into upstream llama.cpp.

Model Details

Property	Value
Base model	IFM/K2-Horizon-0.9B
Architecture	`K2HorizonForCausalLM` (`k2_horizon`)
Parameters	~0.9B (dense decoder, no MoE)
Original dtype	BF16
Source GGUF	IFM/K2-Horizon-0.9B-GGUF
llama.cpp fork	MBZUAI-IFM/llama.cpp @ model/K2Horizon

Note: These GGUFs carry the k2-horizon architecture token and require the MBZUAI-IFM fork (or upstream llama.cpp once support is merged) to run. Vanilla upstream llama.cpp (as of September 2026) does not support K2HorizonForCausalLM.

Included Files

Standard Quantizations

File	Bits/Weight	Notes
`K2-Horizon-0.9B-BF16.gguf`	16 bpw	Source quant, full precision
`K2-Horizon-0.9B-Q8_0.gguf`	8 bpw	Near-lossless, recommended reference
`K2-Horizon-0.9B-Q6_K.gguf`	6 bpw	Near-lossless K-quant
`K2-Horizon-0.9B-Q5_K_M.gguf`	5 bpw	Best quality/size in the 5-bit range
`K2-Horizon-0.9B-Q5_K_S.gguf`	5 bpw	Smaller 5-bit variant
`K2-Horizon-0.9B-Q5_1.gguf`	5 bpw	Legacy 5-bit
`K2-Horizon-0.9B-Q5_0.gguf`	5 bpw	Legacy 5-bit
`K2-Horizon-0.9B-Q4_K_M.gguf`	4 bpw	Recommended general use
`K2-Horizon-0.9B-Q4_K_S.gguf`	4 bpw	Smaller 4-bit K-quant
`K2-Horizon-0.9B-Q4_1.gguf`	4 bpw	Legacy 4-bit
`K2-Horizon-0.9B-Q4_0.gguf`	4 bpw	Legacy 4-bit
`K2-Horizon-0.9B-Q3_K_L.gguf`	3 bpw	Large 3-bit K-quant
`K2-Horizon-0.9B-Q3_K_M.gguf`	3 bpw	Medium 3-bit K-quant
`K2-Horizon-0.9B-Q3_K_S.gguf`	3 bpw	Small 3-bit K-quant
`K2-Horizon-0.9B-Q2_K.gguf`	2 bpw	Aggressive compression
`K2-Horizon-0.9B-Q2_K_S.gguf`	2 bpw	Smaller 2-bit K-quant (imatrix-guided)
`K2-Horizon-0.9B-Q2_0.gguf`	2.25 bpw	Group-64 2-bit
`K2-Horizon-0.9B-Q1_0.gguf`	1.125 bpw	Maximum compression

IQ (Importance-Matrix) Quantizations

File	Bits/Weight
`K2-Horizon-0.9B-IQ4_NL.gguf`	~4 bpw
`K2-Horizon-0.9B-IQ4_XS.gguf`	~4 bpw
`K2-Horizon-0.9B-IQ3_M.gguf`	~3 bpw
`K2-Horizon-0.9B-IQ3_S.gguf`	~3 bpw
`K2-Horizon-0.9B-IQ3_XS.gguf`	~3 bpw
`K2-Horizon-0.9B-IQ3_XXS.gguf`	~3 bpw
`K2-Horizon-0.9B-IQ2_M.gguf`	~2 bpw
`K2-Horizon-0.9B-IQ2_S.gguf`	~2 bpw
`K2-Horizon-0.9B-IQ2_XS.gguf`	~2 bpw
`K2-Horizon-0.9B-IQ2_XXS.gguf`	~2 bpw
`K2-Horizon-0.9B-IQ1_M.gguf`	1.75 bpw
`K2-Horizon-0.9B-IQ1_S.gguf`	1.56 bpw

Quantization Method

Source: IFM's official BF16 GGUF is downloaded directly (no safetensors conversion needed).
imatrix: Computed from the Salesforce/wikitext (wikitext-2-raw-v1) calibration dataset (500 rows). Applied to all K-quants below Q6 and all IQ quants for guided, higher-quality compression.
Fork: MBZUAI-IFM/llama.cpp, branch model/K2Horizon.

Usage

Requires the MBZUAI-IFM llama.cpp fork (model/K2Horizon branch).

# Clone and build the fork
git clone -b model/K2Horizon https://github.com/MBZUAI-IFM/llama.cpp
cd llama.cpp && cmake -B build -DGGML_CUDA=ON && cmake --build build --config Release

# Run inference
./build/bin/llama-cli \
  -m K2-Horizon-0.9B-Q4_K_M.gguf \
  -p "Hello, I am" \
  -n 128

License

Weights are released under the same license as the original IFM/K2-Horizon-0.9B model. Please refer to the original repository for full license terms.

Credits

Original model: MBZUAI IFM
Quantized by: NANI-Nithin
Quantization tool: MBZUAI-IFM/llama.cpp

Downloads last month: 2,998

GGUF

Model size

1B params

Architecture

k2-horizon

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for NANI-Nithin/K2-Horizon-0.9B-GGUF

Base model

IFM/K2-Horizon-0.9B

Quantized

(7)

this model

NANI-Nithin
/

K2-Horizon-0.9B-GGUF

K2-Horizon-0.9B — GGUF Quantizations

Model Details

Included Files

Standard Quantizations

IQ (Importance-Matrix) Quantizations

Quantization Method

Usage

License

Credits

Model tree for NANI-Nithin/K2-Horizon-0.9B-GGUF

Space using NANI-Nithin/K2-Horizon-0.9B-GGUF 1