Instructions to use datasysdev/ann-sparseattention with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use datasysdev/ann-sparseattention with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("datasysdev/ann-sparseattention", dtype="auto")

llama-cpp-python

How to use datasysdev/ann-sparseattention with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="datasysdev/ann-sparseattention",
	filename="gguf/Qwen3-4B-Instruct-2507-F16-ann-6layer-k128-v2.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use datasysdev/ann-sparseattention 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 datasysdev/ann-sparseattention:F16
# Run inference directly in the terminal:
llama cli -hf datasysdev/ann-sparseattention:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf datasysdev/ann-sparseattention:F16
# Run inference directly in the terminal:
llama cli -hf datasysdev/ann-sparseattention:F16

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 datasysdev/ann-sparseattention:F16
# Run inference directly in the terminal:
./llama-cli -hf datasysdev/ann-sparseattention:F16

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 datasysdev/ann-sparseattention:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf datasysdev/ann-sparseattention:F16

Use Docker

docker model run hf.co/datasysdev/ann-sparseattention:F16

LM Studio
Jan
Ollama
How to use datasysdev/ann-sparseattention with Ollama:
```
ollama run hf.co/datasysdev/ann-sparseattention:F16
```

Unsloth Studio

How to use datasysdev/ann-sparseattention with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for datasysdev/ann-sparseattention to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for datasysdev/ann-sparseattention to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for datasysdev/ann-sparseattention to start chatting

How to use datasysdev/ann-sparseattention with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf datasysdev/ann-sparseattention:F16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "datasysdev/ann-sparseattention:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use datasysdev/ann-sparseattention with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf datasysdev/ann-sparseattention:F16

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 datasysdev/ann-sparseattention:F16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use datasysdev/ann-sparseattention with Docker Model Runner:
```
docker model run hf.co/datasysdev/ann-sparseattention:F16
```

Lemonade

How to use datasysdev/ann-sparseattention with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull datasysdev/ann-sparseattention:F16

Run and chat with the model

lemonade run user.ann-sparseattention-F16

List all available models

lemonade list

ann-sparseattention / artifacts /scaling_analysis.md

datasysdev

Correct asymptotic scoring analysis

0585058 verified about 2 months ago

preview code

Raw

History Blame Contribute Delete

2.05 kB

Candidate-Scoring Operation Count

This is an analytic operation-count proxy, not a wall-clock benchmark. It counts the per-query work to identify candidate keys before running the sparse attention softmax and value multiply over the selected keys.

Assumptions

Native head dimension: d_head = 128.
Learned search dimension: d_search = 128.
Quest page size: page_size = 16.
HNSW parameters: M = 32, ef_search = 64.

Per-query scoring formulas:

Full attention: N * d_head = N * 128.
Quest: (N / page_size) * 2 * d_head = N * 16.
Learned HNSW: M * ef_search * log2(N) * d_search = 262,144 * log2(N).

Under these constants, the Quest/HNSW operation-count crossover is approximately 297,937 tokens. Smaller HNSW settings move the crossover earlier; higher-recall settings move it later.

Table

Context	Full ops/query	Quest ops/query	Learned HNSW ops/query	Quest / learned
4K	512,000	64,000	3,136,759	0.02x
8K	1,024,000	128,000	3,398,903	0.04x
16K	2,048,000	256,000	3,661,047	0.07x
32K	4,096,000	512,000	3,923,191	0.13x
64K	8,192,000	1,024,000	4,185,335	0.24x
128K	16,384,000	2,048,000	4,447,479	0.46x
256K	32,768,000	4,096,000	4,709,623	0.87x
512K	65,536,000	8,192,000	4,971,767	1.65x
1M	128,000,000	16,000,000	5,224,942	3.06x
2M	256,000,000	32,000,000	5,487,086	5.83x
4M	512,000,000	64,000,000	5,749,230	11.13x

Interpretation

Quest is cheaper than this high-recall HNSW proxy below the few-hundred-thousand-token regime. At 1M context, Quest costs about 16M scalar ops/query while learned HNSW costs about 5.2M, a roughly 3x operation-count advantage for learned projections.

This does not establish production wall-clock speedup. That still requires GPU-resident ANN retrieval and decode/KV-cache integration. Memory bandwidth may further favor learned ANN at very long context, but that is not included in this FLOP-only proxy.