Instructions to use PollardWeights/K2-Horizon-0.9B-Pollard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use PollardWeights/K2-Horizon-0.9B-Pollard 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 PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S
# Run inference directly in the terminal:
llama cli -hf PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S
# Run inference directly in the terminal:
llama cli -hf PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S

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 PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S
# Run inference directly in the terminal:
./llama-cli -hf PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S

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 PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S

Use Docker

docker model run hf.co/PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S

LM Studio
Jan

vLLM

How to use PollardWeights/K2-Horizon-0.9B-Pollard with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PollardWeights/K2-Horizon-0.9B-Pollard"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PollardWeights/K2-Horizon-0.9B-Pollard",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S

Ollama
How to use PollardWeights/K2-Horizon-0.9B-Pollard with Ollama:
```
ollama run hf.co/PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S
```
Unsloth Desktop

How to use PollardWeights/K2-Horizon-0.9B-Pollard with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S

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": "PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use PollardWeights/K2-Horizon-0.9B-Pollard with Docker Model Runner:
```
docker model run hf.co/PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S
```

Lemonade

How to use PollardWeights/K2-Horizon-0.9B-Pollard with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S

Run and chat with the model

lemonade run user.K2-Horizon-0.9B-Pollard-IQ3_S

List all available models

lemonade list

Hermes Agent

How to use PollardWeights/K2-Horizon-0.9B-Pollard with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S

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 PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use PollardWeights/K2-Horizon-0.9B-Pollard with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S

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 "PollardWeights/K2-Horizon-0.9B-Pollard:IQ3_S" \
  --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 — Pollard

Pollard shrank this model: 2.16 GB (f16) → 0.57 GB — 74% smaller, 3.8× down.

The smallest rung here; larger, higher-fidelity rungs are listed below.

format this model's size

f16 2.16 GB

Q8_0 ~1.15 GB

Q6_K 0.89 GB

Q5_K_M 0.73 GB

PollardMix (this repo's IQ3_S) 0.57 GB

format	this model's size
f16	2.16 GB
Q8_0	~1.15 GB
Q6_K	0.89 GB
Q5_K_M	0.73 GB
PollardMix (this repo's IQ3_S)	0.57 GB

Pollard builds of IFM/K2-Horizon-0.9B made with Pollard Weights — a ladder of measured-allocation quants (bits placed by per-layer sensitivity, not a uniform crush).

Standard GGUF — measured K/i-quant ladder (no trellis flagship yet: the k2-horizon arch isn't in ik_llama.cpp). Runs in a recent llama.cpp / Ollama / LM Studio (see Errata).

Available files (wikitext-2 test, ctx 512)

f16 reference PPL 13.01.

file	PPL	size	Mean KLD	notes
`K2-Horizon-0.9B-Pollard-IQ3_S.gguf`	14.50	0.57 GB	—	smallest
`K2-Horizon-0.9B-Pollard-Q5_K_M.gguf`	13.27	0.73 GB	—	recommended default
`K2-Horizon-0.9B-Pollard-Q6_K.gguf`	13.05	0.89 GB	—	near-lossless

Usage

llama-cli -m K2-Horizon-0.9B-Pollard-Q5_K_M.gguf -p "Explain why the sky is blue." --temp 0.7
ollama run hf.co/PollardWeights/K2-Horizon-0.9B-Pollard

Errata

Requires a recent llama.cpp with k2-horizon architecture support — older builds report unknown architecture 'k2-horizon'. The arch currently ships in the MBZUAI-IFM/llama.cpp fork (branch model/K2Horizon); it runs in stock llama.cpp / Ollama / LM Studio once merged upstream.
Trellis (IQ*_KT) quants need ik_llama.cpp to build/run; K-quants run in any recent llama.cpp.
Measured allocation places bits by per-layer sensitivity under a size budget, on a Calib 3.0 imatrix.
Single machine; replication invited.

Built with Pollard Weights — frontier models, small hardware, no compromise.

Downloads last month: -

GGUF

Model size

1B params

Architecture

k2-horizon

Hardware compatibility

3-bit

5-bit

6-bit

Model tree for PollardWeights/K2-Horizon-0.9B-Pollard

Base model

IFM/K2-Horizon-0.9B

Quantized

(5)

this model

PollardWeights
/

K2-Horizon-0.9B-Pollard

K2-Horizon-0.9B — Pollard

Pollard shrank this model: 2.16 GB (f16) → 0.57 GB — 74% smaller, 3.8× down.

Available files (wikitext-2 test, ctx 512)

Usage

Errata

Model tree for PollardWeights/K2-Horizon-0.9B-Pollard