Instructions to use notSnix/Step-3.7-Flash-MTP-Draft-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use notSnix/Step-3.7-Flash-MTP-Draft-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="notSnix/Step-3.7-Flash-MTP-Draft-GGUF",
	filename="Step-3.7-Flash-MTP-BF16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use notSnix/Step-3.7-Flash-MTP-Draft-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M

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 notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M

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 notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M

Use Docker

docker model run hf.co/notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use notSnix/Step-3.7-Flash-MTP-Draft-GGUF with Ollama:
```
ollama run hf.co/notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M
```

Unsloth Studio

How to use notSnix/Step-3.7-Flash-MTP-Draft-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 notSnix/Step-3.7-Flash-MTP-Draft-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 notSnix/Step-3.7-Flash-MTP-Draft-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for notSnix/Step-3.7-Flash-MTP-Draft-GGUF to start chatting

Docker Model Runner
How to use notSnix/Step-3.7-Flash-MTP-Draft-GGUF with Docker Model Runner:
```
docker model run hf.co/notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M
```

Lemonade

How to use notSnix/Step-3.7-Flash-MTP-Draft-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull notSnix/Step-3.7-Flash-MTP-Draft-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Step-3.7-Flash-MTP-Draft-GGUF-Q4_K_M

List all available models

lemonade list

Step 3.7 Flash MTP Draft GGUFs

These are companion MTP draft GGUFs for speculative decoding. They are not standalone chat models.

Use them with the full model repo:

notSnix/Step-3.7-Flash-Q4_K_M-GGUF

The draft GGUF is passed with --model-draft; the full model is passed with --model.

Files

File	Size	SHA256	Purpose
`Step-3.7-Flash-MTP-Q8_0.gguf`	3.5 GB	`017de8990140621b5b4af431448f20873fbf0b052f6c50d2afac15f45802a98d`	Recommended MTP draft
`Step-3.7-Flash-MTP-Q6_K.gguf`	2.7 GB	`f41736e0dcce133d0dd0b81e14bd2965091e27dff306a28cec11ceb19fadbf46`	Smaller Q6_K MTP draft
`Step-3.7-Flash-MTP-Q4_K_M.gguf`	2.0 GB	`44118cfe64f45b38127ad6fb626e16bd94ee5a827cb34aa83d9e6df3450aebaf`	Smaller MTP draft
`Step-3.7-Flash-MTP-BF16.gguf`	6.5 GB	`fd811c81d14c786d314d8006655bba61971059abcfdfb6109ce83fd768f8b289`	Experimental BF16 MTP draft

Runtime

Current llama.cpp main supports Step MTP-tail draft loading natively. This was smoke-tested with clean llama.cpp commit d545a2a993849fcf3b752d85ae256fc9d6a9de79.

git clone https://github.com/ggml-org/llama.cpp
cd llama.cpp
cmake -B build-cuda -DGGML_CUDA=ON
cmake --build build-cuda --config Release -j

Usage

llama-server \
  --model Step-3.7-Flash-Q4_K_M.gguf \
  --model-draft Step-3.7-Flash-MTP-Q8_0.gguf \
  --host 0.0.0.0 \
  --port 8000 \
  --ctx-size 262144 \
  --n-gpu-layers all \
  --split-mode layer \
  --parallel 1 \
  --reasoning on \
  --reasoning-format deepseek \
  --spec-type draft-mtp \
  --spec-draft-n-max 2 \
  --spec-draft-p-min 0.60

Which Draft Should I Use?

Use Step-3.7-Flash-MTP-Q8_0.gguf first. It was the best local default in testing.

Use Step-3.7-Flash-MTP-Q6_K.gguf if you want a smaller draft file while staying above Q4.

Use Step-3.7-Flash-MTP-Q4_K_M.gguf if you want the smaller draft file.

Use Step-3.7-Flash-MTP-BF16.gguf for experimentation.

Checksums

sha256sum -c SHA256SUMS

Notes

These files intentionally keep the upstream Step MTP tail-layer numbering (blk.45, blk.46, blk.47).
They are companion speculative-decoding draft GGUFs, not full-model quants.
The full Q4_K_M model is hosted separately so Hugging Face's GGUF widget does not display draft files as tiny full-model quantizations.
This is a community GGUF conversion of the upstream Apache-2.0 model, not an official StepFun release.

Downloads last month: -

GGUF

Model size

3B params

Architecture

step35

Hardware compatibility

4-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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

Model tree for notSnix/Step-3.7-Flash-MTP-Draft-GGUF

Base model

stepfun-ai/Step-3.7-Flash

Quantized

(23)

this model