Instructions to use EvaHap/SmallpoV1H_Beta1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use EvaHap/SmallpoV1H_Beta1 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 EvaHap/SmallpoV1H_Beta1:F16
# Run inference directly in the terminal:
llama cli -hf EvaHap/SmallpoV1H_Beta1:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf EvaHap/SmallpoV1H_Beta1:F16
# Run inference directly in the terminal:
llama cli -hf EvaHap/SmallpoV1H_Beta1: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 EvaHap/SmallpoV1H_Beta1:F16
# Run inference directly in the terminal:
./llama-cli -hf EvaHap/SmallpoV1H_Beta1: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 EvaHap/SmallpoV1H_Beta1:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf EvaHap/SmallpoV1H_Beta1:F16

Use Docker

docker model run hf.co/EvaHap/SmallpoV1H_Beta1:F16

LM Studio
Jan
Ollama
How to use EvaHap/SmallpoV1H_Beta1 with Ollama:
```
ollama run hf.co/EvaHap/SmallpoV1H_Beta1:F16
```

Unsloth Studio

How to use EvaHap/SmallpoV1H_Beta1 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 EvaHap/SmallpoV1H_Beta1 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 EvaHap/SmallpoV1H_Beta1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for EvaHap/SmallpoV1H_Beta1 to start chatting

How to use EvaHap/SmallpoV1H_Beta1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf EvaHap/SmallpoV1H_Beta1: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": "EvaHap/SmallpoV1H_Beta1:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use EvaHap/SmallpoV1H_Beta1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf EvaHap/SmallpoV1H_Beta1: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 EvaHap/SmallpoV1H_Beta1:F16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use EvaHap/SmallpoV1H_Beta1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf EvaHap/SmallpoV1H_Beta1:F16

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 "EvaHap/SmallpoV1H_Beta1:F16" \
  --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"

Docker Model Runner
How to use EvaHap/SmallpoV1H_Beta1 with Docker Model Runner:
```
docker model run hf.co/EvaHap/SmallpoV1H_Beta1:F16
```

Lemonade

How to use EvaHap/SmallpoV1H_Beta1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull EvaHap/SmallpoV1H_Beta1:F16

Run and chat with the model

lemonade run user.SmallpoV1H_Beta1-F16

List all available models

lemonade list

Smallpo V1H(Beta1)

Smallpo团队研发的最新模型，极致的性能和拟人化。

我们十分高兴的告诉各位，我们的Smallpo第一代版本已经发布了。 SmallpoV1H是我们最新、最强的模型，尽管它还处于十分早期的实验阶段，但是Beta1的强大拟人性已经展现出来。我们相信，Smallpo未来可以变得更好！

技术细节

此模型没有什么技术含量，我们使用Unsloth进行训练。相关数据集来源于网络。

现在仍存在的问题

此模型参数量太小，智商低，只能娱乐使用。
此模型经用户报告，模型使用思考功能后有时不会输出回答正文。这是因为模型的数据集中没有包含思考的部分数据。
此模型无法完整输出自己的名字Smallpo，这是因为在训练过程中，我们没有重点训练名字这一板块。
此模型使用除中文外的语言进行对话，效果较差。这是因为模型的数据集中包含除中文外的其他语言占比小。

最后

我们相信，Smallpo未来可以变得更好！本模型使用Qwen3.5-0.8B进行微调训练。本模型使用Unsloth进行训练。

©Smallpo AI

Downloads last month: 27

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for EvaHap/SmallpoV1H_Beta1

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Quantized

(188)

this model