Instructions to use ubergarm/Step-3.5-Flash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ubergarm/Step-3.5-Flash-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ubergarm/Step-3.5-Flash-GGUF",
	filename="IQ4_XS/Step-3.5-Flash-IQ4_XS-00001-of-00004.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ubergarm/Step-3.5-Flash-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ubergarm/Step-3.5-Flash-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama-cli -hf ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ubergarm/Step-3.5-Flash-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama-cli -hf ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

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 ubergarm/Step-3.5-Flash-GGUF:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

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 ubergarm/Step-3.5-Flash-GGUF:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

Use Docker

docker model run hf.co/ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

LM Studio
Jan

vLLM

How to use ubergarm/Step-3.5-Flash-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ubergarm/Step-3.5-Flash-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": "ubergarm/Step-3.5-Flash-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

Ollama
How to use ubergarm/Step-3.5-Flash-GGUF with Ollama:
```
ollama run hf.co/ubergarm/Step-3.5-Flash-GGUF:IQ4_XS
```

Unsloth Studio

How to use ubergarm/Step-3.5-Flash-GGUF 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 ubergarm/Step-3.5-Flash-GGUF 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 ubergarm/Step-3.5-Flash-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ubergarm/Step-3.5-Flash-GGUF to start chatting

How to use ubergarm/Step-3.5-Flash-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

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": "ubergarm/Step-3.5-Flash-GGUF:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ubergarm/Step-3.5-Flash-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

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 ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use ubergarm/Step-3.5-Flash-GGUF with Docker Model Runner:
```
docker model run hf.co/ubergarm/Step-3.5-Flash-GGUF:IQ4_XS
```

Lemonade

How to use ubergarm/Step-3.5-Flash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ubergarm/Step-3.5-Flash-GGUF:IQ4_XS

Run and chat with the model

lemonade run user.Step-3.5-Flash-GGUF-IQ4_XS

List all available models

lemonade list

Step 3.7?

#15

by alfiedotwtf - opened 4 days ago

Discussion

alfiedotwtf

4 days ago

Thank you for the ik_llama imatrix quant :)

I'm just wondering if a Step 3.7 IQ4_KSS is in your future plans?

alfiedotwtf

4 days ago

Also, off topic but I'm not sure where to ask... given you're the biggest releaser of ik_llama tuned KSS models, do you know how/where I can find more? HF's interface doesn't really work for quant searches

ubergarm

Owner 3 days ago

@alfiedotwtf

Thanks, glad you're enjoying the ik quants! I'm not gonna get that one released any time soon, been doing some hardware maintenance and slowed down for the summer at the moment.

Your best bet at the moment is to check out https://huggingface.co/AesSedai/Step-3.7-Flash-GGUF?show_file_info=IQ4_XS%2FStep-3.7-Flash-IQ4_XS-00001-of-00003.gguf which should be fairly close to an iq4_kss though a bit bigger.

where I can find more?

Some folks tag their hf repo with ik_llama.cpp which can help maybe. I've been doing my best to get info out there for other folks to do ik quantizations as well.

What is your local daily driver? I'm still using my Qwen3.6-27B-MTP-IQ4_KS full offload on 24GB VRAM, and with pi.dev harness and a web skill that uses ddgs + primp + rs_trafilatura it replaces most search interfaces fairly well if you're on ip address / vpn in the residential range.

alfiedotwtf

about 5 hours ago

Thanks for your pointers! Also, thanks for another vote for Pi - you gave me the impetus to start using it. Gave it a go Friday night, and it feels like falling in love with Emacs all over again - fun to make it your own. And so I've ditched Opencode for now so I can get a feel for Pi :)

I've been using Step 3.5 for a while now, but only the past few days I've been trying out MiniMax 2.7... thinking to stick to it for a while (if it borks out I'll try Step 3.7).

... gotta say, these past few months feel like the Wild West online again. It's been a blast with new models and new engines coming out like a fire hose.

alfiedotwtf changed discussion status to closed about 5 hours ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment