Instructions to use AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF",
	filename="Step-3.7-Flash-AEON-Ultimate-Abliterated-IQ1_M-00001-of-00002.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_M
# Run inference directly in the terminal:
llama-cli -hf AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_M
# Run inference directly in the terminal:
llama-cli -hf AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_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 AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_M
# Run inference directly in the terminal:
./llama-cli -hf AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_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 AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_M

Use Docker

docker model run hf.co/AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_M

LM Studio
Jan

vLLM

How to use AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-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": "AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_M

Ollama
How to use AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF with Ollama:
```
ollama run hf.co/AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_M
```

Unsloth Studio

How to use AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-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 AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-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 AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF to start chatting

How to use AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_M

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": "AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-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 AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_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 AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_M

Run Hermes

hermes

Docker Model Runner
How to use AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_M
```

Lemonade

How to use AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF:IQ1_M

Run and chat with the model

lemonade run user.Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF-IQ1_M

List all available models

lemonade list

⚠️ KNOWN BROKEN — do not use for inference yet (fix in progress)

These GGUFs currently produce garbled output. The cause is NOT an upstream llama.cpp engine bug — any earlier note on this card claiming an "engine-blocked" / PR-#23845 dependency is outdated; please disregard it. The official Step-3.7 GGUF runs fine on a correctly-built llama.cpp.

Root cause: our Expert-Granular Abliteration interacts badly with low-bit quantization (same as our NVFP4) — the ablation zeroes a residual-stream subspace that is exact at BF16 but re-corrupted by quant noise at 3–4 bit → garbage. Coherent output requires BF16.

✅ Use instead: the BF16 release. A milder-ablation re-quant that survives low-bit is being validated; these files will be replaced or withdrawn once fixed.

Step-3.7-Flash-AEON-Ultimate-Abliterated-GGUF ⚠️ EXPERIMENTAL

GGUF quants of AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-BF16 (198B / ~11B-active sparse-MoE vision-language thinking model), built for single-DGX-Spark deployment.

⚠️ EXPERIMENTAL — NOT YET FUNCTIONAL (engine-blocked)

These GGUFs currently produce garbage output on every available GGUF runtime (llama.cpp, Ollama, LM Studio, KoboldCpp — all share the same engine). The cause is not these files — the quantized weights, abliteration, and tokenizer are all verified correct. The blocker is an open upstream bug in llama.cpp's Step-3.7 inference graph: Step-3.7 is routed through the step35 compute graph, which mis-runs its forward pass (garbage from the first token, independent of bit-width — even the near-lossless q8_0 is affected).

Dependency to use these properly: a corrected llama.cpp Step-3.7 inference implementation (tracking ggml-org/llama.cpp#23845 / a StepFun-fork fix). They are expected to work as-is once that lands — no re-quantization needed.

(Tokenizer note: it is correct. The right pre-tokenizer is deepseek-v3 — if a build defaults otherwise, pass --override-kv tokenizer.ggml.pre=str:deepseek-v3. This is a minor correctness item, not the blocker.)

Status: experimental until functionality is confirmed on a fixed engine. For working deployment today, use the BF16 or NVFP4 releases (table below).

Model family — formats, quality, validation

Release	Format	Size	Target hardware	Quality	Refusals removed	Validation state
…-BF16	BF16 safetensors	376 GB	multi-GPU (≥2× Spark / Blackwell)	reference (full)	✅ d≈10→0.35	✅ working; weight-verified, prefill refusal-collapse confirmed
…-NVFP4	NVFP4 W4A4 (modelopt)	124 GB	2× DGX Spark (TP=2)	near-full (RT err 0.095)	✅	✅ working path; weight-verified (down 0.095; o_proj/up bit-exact)
…-GGUF / q8_0	GGUF (exp)	209 GB	(near-lossless base)	near-lossless	✅ (weights)	⚠️ experimental — engine-blocked
…-GGUF / Q3_K_M	GGUF dynamic (exp)	~101 GB	1× DGX Spark	high (3-bit dyn.)	✅ (weights)	⚠️ experimental — engine-blocked
…-GGUF / IQ1_M	GGUF dynamic (exp)	48 GB (~1.95 bpw)	1× DGX Spark (max KV headroom)	low (1.5-bit; below IQ2 cliff)	✅ (weights)	⚠️ experimental — engine-blocked

Legend: ✅ working today · ⚠️ experimental, awaiting the upstream engine fix.

Two independent things this build is

Abliterated (behavior) — refusals removed via Expert-Granular Abliteration across all 288 experts (refusal subspace collapsed from Cohen's d≈10 → 0.35). Uncensored.
Precisely quantized (fidelity) — a data-driven, per-component mixed-precision scheme + our own imatrix, not a uniform low-bit dump. Capable + still-uncensored after quantization (when the engine runs it).

Quantization methodology (data-driven selective allocation)

Per-component bits from our outlier study + refusal-subspace map (not stock Q3_K_M):

Component	Q3_K_M tier	IQ1_M tier	Rationale (measured)
Expert `gate/up_proj`	Q3_K	IQ1_M	cleanest family (FP4-g16 err 0.094) → bulk savings
Expert `down_proj`	Q4_K	IQ2_XXS	most quant-sensitive expert block
`self_attn.o_proj`	Q6_K	Q5_K	13.1× outlier
q/k/v, attn-gate	Q5_K	Q4_K	—
`share_expert.*`	Q5/Q6_K	Q4/Q5_K	shared.down 18.7× outlier
dense MLP (L0–2)	Q5_K	Q4_K	dense.down 24× outlier
router (`ffn_gate_inp`)	FP32	FP32	routing fully preserved
embed / output	Q6_K	Q4/Q5_K	—
vision (mmproj)	F16	F16	kept

Plus a custom imatrix (diverse general/reasoning/code calibration).

Inference (once a fixed Step-3.7 engine is available)

# Build the StepFun step3.7 llama.cpp fork (or a future fixed mainline)
git clone -b step3.7 https://github.com/stepfun-ai/llama.cpp && cd llama.cpp
cmake -B build -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=121 && cmake --build build -j --config Release

# Serve (shards auto-load from the first piece; mmproj for vision)
./build/bin/llama-server \
  -m  Step-3.7-Flash-…-Q3_K_M-00001-of-0000N.gguf \
  --mmproj mmproj-step3.7-flash-f16.gguf \
  --cache-type-k q8_0 --cache-type-v q8_0 \
  -c 131072 --parallel 4 -ngl 999 --flash-attn \
  --override-kv tokenizer.ggml.pre=str:deepseek-v3 \
  --host 0.0.0.0 --port 8080

This will emit garbage until the upstream Step-3.7 graph bug (#23845) is fixed. Q3_K_M targets one Spark with moderate KV headroom; IQ1_M maximizes headroom (quality-tolerant, below the IQ2 cliff); q8_0 is the near-lossless base.

Quantized on NVIDIA B300 via the StepFun step3.7 llama.cpp fork + custom imatrix, from the AEON-Ultimate abliterated BF16. Base model © StepFun AI, Apache-2.0.