Instructions to use Ex0bit/Step-3.5-Flash-PRISM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ex0bit/Step-3.5-Flash-PRISM with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Ex0bit/Step-3.5-Flash-PRISM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Ex0bit/Step-3.5-Flash-PRISM", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Ex0bit/Step-3.5-Flash-PRISM 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 Ex0bit/Step-3.5-Flash-PRISM:IQ2_M
# Run inference directly in the terminal:
llama cli -hf Ex0bit/Step-3.5-Flash-PRISM:IQ2_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ex0bit/Step-3.5-Flash-PRISM:IQ2_M
# Run inference directly in the terminal:
llama cli -hf Ex0bit/Step-3.5-Flash-PRISM:IQ2_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 Ex0bit/Step-3.5-Flash-PRISM:IQ2_M
# Run inference directly in the terminal:
./llama-cli -hf Ex0bit/Step-3.5-Flash-PRISM:IQ2_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 Ex0bit/Step-3.5-Flash-PRISM:IQ2_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ex0bit/Step-3.5-Flash-PRISM:IQ2_M

Use Docker

docker model run hf.co/Ex0bit/Step-3.5-Flash-PRISM:IQ2_M

LM Studio
Jan

vLLM

How to use Ex0bit/Step-3.5-Flash-PRISM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ex0bit/Step-3.5-Flash-PRISM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/Step-3.5-Flash-PRISM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ex0bit/Step-3.5-Flash-PRISM:IQ2_M

SGLang

How to use Ex0bit/Step-3.5-Flash-PRISM with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Ex0bit/Step-3.5-Flash-PRISM" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/Step-3.5-Flash-PRISM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Ex0bit/Step-3.5-Flash-PRISM" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/Step-3.5-Flash-PRISM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Ex0bit/Step-3.5-Flash-PRISM with Ollama:
```
ollama run hf.co/Ex0bit/Step-3.5-Flash-PRISM:IQ2_M
```

Unsloth Studio

How to use Ex0bit/Step-3.5-Flash-PRISM 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 Ex0bit/Step-3.5-Flash-PRISM 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 Ex0bit/Step-3.5-Flash-PRISM to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ex0bit/Step-3.5-Flash-PRISM to start chatting

How to use Ex0bit/Step-3.5-Flash-PRISM with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ex0bit/Step-3.5-Flash-PRISM:IQ2_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": "Ex0bit/Step-3.5-Flash-PRISM:IQ2_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Ex0bit/Step-3.5-Flash-PRISM with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ex0bit/Step-3.5-Flash-PRISM:IQ2_M

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 "Ex0bit/Step-3.5-Flash-PRISM:IQ2_M" \
  --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 Ex0bit/Step-3.5-Flash-PRISM with Docker Model Runner:
```
docker model run hf.co/Ex0bit/Step-3.5-Flash-PRISM:IQ2_M
```

Lemonade

How to use Ex0bit/Step-3.5-Flash-PRISM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ex0bit/Step-3.5-Flash-PRISM:IQ2_M

Run and chat with the model

lemonade run user.Step-3.5-Flash-PRISM-IQ2_M

List all available models

lemonade list

Hermes Agent

How to use Ex0bit/Step-3.5-Flash-PRISM with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ex0bit/Step-3.5-Flash-PRISM:IQ2_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 Ex0bit/Step-3.5-Flash-PRISM:IQ2_M

Run Hermes

hermes

Atomic Chat

Step-3.5-Flash-PRISM / README.md

Ex0bit

Update README.md

815ba11 verified 6 months ago

preview code

Raw

History Blame Contribute Delete

5.11 kB

	---
	license: other
	license_name: prism-research
	license_link: LICENSE.md
	language:
	- en
	- zh
	tags:
	- stepfun
	- prism
	- moe
	- reasoning
	- coding
	- agentic
	- abliterated
	pipeline_tag: text-generation
	library_name: transformers
	base_model:
	- stepfun-ai/Step-3.5-Flash
	base_model_relation: finetune
	---

	[![Parameters](https://img.shields.io/badge/Parameters-196B_(11B_Active)-blue)]()
	[![Architecture](https://img.shields.io/badge/Architecture-MoE-green)]()
	[![Context](https://img.shields.io/badge/Context-256K-orange)]()
	[![MTP](https://img.shields.io/badge/MTP--3-350_tok%2Fs_Peak-purple)]()


	<p align="center">
	<img src="https://cdn-uploads.huggingface.co/production/uploads/63adf1fa42fd3b8dbaeb0c92/NkmQvQUXzckiRb8U__203.png" width="400"/>
	</p>

	# Step-3.5-Flash-PRISM

	A "role-play" following unrestricted/unchained PRISM-LITE version of [StepFun's Step 3.5 Flash](https://huggingface.co/stepfun-ai/Step-3.5-Flash) intended particularly for over-refusal and propaganda mechanisms suppression using our SOTA PRISM pipeline.

	PRISM-PRO version avialable here: hhttps://ko-fi.com/s/d70e27c5b5

	For Full Custom Production PRISM versions & raw tensors reach out @ https://ko-fi.com/ex0bit.
	<div align="center">

	### ☕ Support Our Work

	If you enjoy our work and find it useful, please consider sponsoring or supporting us!

	[![Ko-fi](https://img.shields.io/badge/Ko--fi-Support%20Us-ff5e5b?logo=ko-fi&logoColor=white)](https://ko-fi.com/ericelbaz)

	\| Option \| Description \|
	\|--------\|-------------\|
	\| [PRISM VIP Membership](https://ko-fi.com/summary/6bae206c-a751-4868-8dc7-f531afd1fb4c) \| Access to all PRISM models \|
	\| Bitcoin \| `bc1qarq2pyn4psjpcxzp2ghgwaq6y2h4e53q232x8r` \|

	![image](https://cdn-uploads.huggingface.co/production/uploads/63adf1fa42fd3b8dbaeb0c92/Psgbl1TgyDok__C7AMQog.png)

	</div>

	---

	## Model Highlights

	- PRISM Ablation — State-of-the-art technique that removes over-refusal behaviors while preserving model capabilities
	- 196B MoE Architecture — 196 billion total parameters with only 11 billion active per token across 288 fine-grained routed experts + 1 shared expert
	- Multi-Token Prediction (MTP-3) — Predicts 4 tokens simultaneously, achieving 100–300 tok/s typical throughput (peaking at 350 tok/s)
	- 256K Context Window — Cost-efficient long context via 3:1 Sliding Window Attention (SWA) ratio
	- Frontier Reasoning & Coding — 97.3 on AIME 2025, 74.4% on SWE-bench Verified, 51.0% on Terminal-Bench 2.0
	- Accessible Local Deployment — Runs on high-end consumer hardware (Mac Studio M4 Max, NVIDIA DGX Spark)

	## Model Architecture

	\| Specification \| Value \|
	\|---------------\|-------\|
	\| Architecture \| Sparse Mixture-of-Experts (MoE) \|
	\| Backbone \| 45-layer Transformer (4,096 hidden dim) \|
	\| Total Parameters \| 196.81B (196B Backbone + 0.81B Head) \|
	\| Activated Parameters \| ~11B (per token) \|
	\| Routed Experts per Layer \| 288 \|
	\| Shared Experts \| 1 (always active) \|
	\| Selected Experts per Token \| Top-8 \|
	\| Vocabulary Size \| 128,896 \|
	\| Context Length \| 256K \|
	\| Attention \| Hybrid SWA (3:1 SWA-to-Full ratio) \|
	\| MTP Head \| Sliding-window attention + dense FFN (4 tokens/pass) \|

	## Benchmarks

	\| Benchmark \| Step 3.5 Flash \| DeepSeek V3.2 \| Kimi K2.5 \| GLM-4.7 \| MiniMax M2.1 \|
	\|-----------\|---------------\|---------------\|-----------\|---------\|--------------\|
	\| Agent \| \| \| \| \| \|
	\| τ²-Bench \| 88.2 \| 80.3 \| 85.4 \| 87.4 \| 86.6 \|
	\| BrowseComp \| 51.6 \| 51.4 \| 60.6 \| 52.0 \| 47.4 \|
	\| GAIA (no file) \| 84.5 \| 75.1 \| 75.9 \| 61.9 \| 64.3 \|
	\| xbench-DeepSearch (2025.05) \| 83.7 \| 78.0 \| 76.7 \| 72.0 \| 68.7 \|
	\| Reasoning \| \| \| \| \| \|
	\| AIME 2025 \| 97.3 \| 93.1 \| 96.1 \| 95.7 \| 83.0 \|
	\| HMMT 2025 (Feb.) \| 98.4 \| 92.5 \| 95.4 \| 97.1 \| 71.0 \|
	\| IMOAnswerBench \| 85.4 \| 78.3 \| 81.8 \| 82.0 \| 60.4 \|
	\| Coding \| \| \| \| \| \|
	\| LiveCodeBench-V6 \| 86.4 \| 83.3 \| 85.0 \| 84.9 \| — \|
	\| SWE-bench Verified \| 74.4 \| 73.1 \| 76.8 \| 73.8 \| 74.0 \|
	\| Terminal-Bench 2.0 \| 51.0 \| 46.4 \| 50.8 \| 41.0 \| 47.9 \|


	### llama.cpp (GGUF)

	For local deployment (requires ~120 GB VRAM for int4, smaller quants are available):

	```bash
	./llama-cli -m step3.5_flash_prism_Q4_K_S.gguf --jinja
	```

	## Recommended Parameters

	\| Use Case \| Temperature \| Top-P \| Max New Tokens \|
	\|----------\|-------------\|-------\|----------------\|
	\| Reasoning / Coding \| 1.0 \| 0.95 \| 32768 \|
	\| General Chat \| 0.6 \| 0.95 \| 4096 \|

	## Hardware Requirements

	\| Setup \| Details \|
	\|-------\|---------\|
	\| BF16 (Full) \| 8x H100/A100 80GB with tensor parallelism \|
	\| FP8 Quantized \| 8x A100 80GB with expert parallelism \|
	\| GGUF INT4 (Local) \| ~120 GB unified memory (Mac Studio M4 Max 128GB, DGX Spark, AMD Ryzen AI Max+ 395) \|

	## License

	This model is released under the [PRISM Research License](LICENSE.md).

	## Acknowledgments

	Based on [Step 3.5 Flash](https://huggingface.co/stepfun-ai/Step-3.5-Flash) by [StepFun AI](https://www.stepfun.com). See the [technical report](https://github.com/stepfun-ai/Step-3.5-Flash/blob/main/step_3p5_flash_tech_report.pdf) and [blog post](https://static.stepfun.com/blog/step-3.5-flash/) for more details on the base model.