Instructions to use VexelQuant/vx-alphadesk-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use VexelQuant/vx-alphadesk-test 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 VexelQuant/vx-alphadesk-test:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf VexelQuant/vx-alphadesk-test:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf VexelQuant/vx-alphadesk-test:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf VexelQuant/vx-alphadesk-test:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf VexelQuant/vx-alphadesk-test:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf VexelQuant/vx-alphadesk-test:Q4_K_M

Use Docker

docker model run hf.co/VexelQuant/vx-alphadesk-test:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use VexelQuant/vx-alphadesk-test with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/VexelQuant/vx-alphadesk-test:Q4_K_M

Ollama
How to use VexelQuant/vx-alphadesk-test with Ollama:
```
ollama run hf.co/VexelQuant/vx-alphadesk-test:Q4_K_M
```
Unsloth Desktop

How to use VexelQuant/vx-alphadesk-test with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VexelQuant/vx-alphadesk-test: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": "VexelQuant/vx-alphadesk-test:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use VexelQuant/vx-alphadesk-test with Docker Model Runner:
```
docker model run hf.co/VexelQuant/vx-alphadesk-test:Q4_K_M
```

Lemonade

How to use VexelQuant/vx-alphadesk-test with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull VexelQuant/vx-alphadesk-test:Q4_K_M

Run and chat with the model

lemonade run user.vx-alphadesk-test-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use VexelQuant/vx-alphadesk-test with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VexelQuant/vx-alphadesk-test: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 VexelQuant/vx-alphadesk-test:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use VexelQuant/vx-alphadesk-test with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VexelQuant/vx-alphadesk-test: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 "VexelQuant/vx-alphadesk-test: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"

AlphaDesk Perp Engine (`vx-alphadesk-test`)

Dedicated institutional quantitative execution model trained by VexelQuant Research (https://vexelquant.me). Enforces 100.0% schema compliance at token generation time with <20ms latency SLA.

Architecture

Base Backbone: Qwen/Qwen2.5-1.5B-Instruct
Alignment: 4-bit QLoRA SFT + dynamic GRPO schema alignment
Grammar Engine: GBNF (schema.gbnf)

Audited 50-Row Verification

Schema Match Rate: 100.0%
p50 Latency: 1985.15ms
p99 Latency: 2207.4ms
Total Tested Rows: 50 / 50

Schema Definition

from pydantic import BaseModel, ConfigDict, Field
from typing import Literal, List

class ClientStructuredOutput(BaseModel):
    model_config = ConfigDict(extra="forbid", strict=True)
    pair: str
    side: Literal["LONG", "SHORT", "FLAT"]
    leverage: int
    size_usdc: float

Turnkey 1-Command Deployment

unzip vx-alphadesk-test-local-node-dropin.zip
cd vexel-local-node
docker compose up -d

Downloads last month: -

Safetensors

Model size

2B params

Tensor type

F16

Model tree for VexelQuant/vx-alphadesk-test

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Quantized

(375)

this model

AlphaDesk Perp Engine (vx-alphadesk-test)

Architecture

Audited 50-Row Verification

Schema Definition

Turnkey 1-Command Deployment

Model tree for VexelQuant/vx-alphadesk-test

AlphaDesk Perp Engine (`vx-alphadesk-test`)