Instructions to use mixer3d/step-3.5-flash-imatrix-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mixer3d/step-3.5-flash-imatrix-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mixer3d/step-3.5-flash-imatrix-gguf",
	filename="step-3.5-flash-q4_k_s-00001-of-00003.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use mixer3d/step-3.5-flash-imatrix-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_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 mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_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 mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_S

Use Docker

docker model run hf.co/mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_S

LM Studio
Jan

vLLM

How to use mixer3d/step-3.5-flash-imatrix-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mixer3d/step-3.5-flash-imatrix-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": "mixer3d/step-3.5-flash-imatrix-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_S

Ollama
How to use mixer3d/step-3.5-flash-imatrix-gguf with Ollama:
```
ollama run hf.co/mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_S
```

Unsloth Studio

How to use mixer3d/step-3.5-flash-imatrix-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 mixer3d/step-3.5-flash-imatrix-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 mixer3d/step-3.5-flash-imatrix-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mixer3d/step-3.5-flash-imatrix-gguf to start chatting

How to use mixer3d/step-3.5-flash-imatrix-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_S

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": "mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mixer3d/step-3.5-flash-imatrix-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 mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_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 mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_S

Run Hermes

hermes

Docker Model Runner
How to use mixer3d/step-3.5-flash-imatrix-gguf with Docker Model Runner:
```
docker model run hf.co/mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_S
```

Lemonade

How to use mixer3d/step-3.5-flash-imatrix-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mixer3d/step-3.5-flash-imatrix-gguf:Q4_K_S

Run and chat with the model

lemonade run user.step-3.5-flash-imatrix-gguf-Q4_K_S

List all available models

lemonade list

step-3.5-flash-imatrix-gguf

This repo contains GGUF weights for stepfun-ai/Step-3.5-Flash with imatrix. Tested on strix halo.

This imatrix version fits into ~104 GiB of VRAM/RAM, saving roughly 7 GiB compared to the standard Q4_K_M, while actually providing slightly better output quality (lower perplexity).

Performance & Efficiency Benchmark (Strix Halo)

This model was tested on the AMD Strix Halo platform (Debian, Kernel 6.18.5) using llama.cpp 7966 (8872ad212) with two different backends: ROCm and Vulkan.

Key Findings:

ROCm is more efficient: For a full benchmark run, ROCm was 4.7x faster and consumed 65% less energy than Vulkan.
Prompt Processing: ROCm dominates in prompt ingestion speed, reaching over 350 t/s for short contexts and maintaining much higher throughput as context grows.
Token Generation: Vulkan shows slightly higher raw generation speeds (T/s) for small contexts, but at a significantly higher energy cost. Not efficient with CTX >= 8k.
Context Scaling: The model remains usable and tested up to 131k context, though energy costs scale exponentially on the Vulkan backend compared to a more linear progression on ROCm.

Backend	Total Time	Total Energy
ROCm	31m 14s	60.63 Wh
Vulkan	149m 03s	175.47 Wh

Full performance charts (Power, T/s, Energy) are available in the image below.

Memory Requirements & Comparison

Quantization	Size (Binary GiB)	Size (Decimal GB)	PPL (Perplexity)
Q4_K_S (imatrix) THIS VERSION	104 GiB	111 GB	2.4130
Q4_K_M (standard)	111 GiB	119 GB	2.4177

Quantization Details

Method: llama-quantize
Llama.cpp Version: 7966 (8872ad212)
Original Model Precision: BF16
imatrix with wikitext-103-raw-v1

Files Provided

File	Quant Method	Size	Description
`step-3.5-flash-q4_k_s-0000{1..3}-of-00003.gguf`	Q4_K_S	104 GB	High quality, with imatrix great for strix-halo

Usage

You can use these models with llama.cpp

./llama-server -m step-3.5-flash-q4_k_s-00001-of-00003.gguf -no-mmap -ngl 99 --port 8080 -c 0 -fa 1 --jinja

Downloads last month: 27

GGUF

Model size

197B params

Architecture

step35

Hardware compatibility

4-bit

Model tree for mixer3d/step-3.5-flash-imatrix-gguf

Base model

stepfun-ai/Step-3.5-Flash

Quantized

(25)

this model