Instructions to use GestaltLabs/Ornstein-3.5-9B-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GestaltLabs/Ornstein-3.5-9B-V2 with Transformers:

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

pipe = pipeline("text-generation", model="GestaltLabs/Ornstein-3.5-9B-V2")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("GestaltLabs/Ornstein-3.5-9B-V2")
model = AutoModelForMultimodalLM.from_pretrained("GestaltLabs/Ornstein-3.5-9B-V2")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use GestaltLabs/Ornstein-3.5-9B-V2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="GestaltLabs/Ornstein-3.5-9B-V2",
	filename="ornstein-v2-bf16.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 GestaltLabs/Ornstein-3.5-9B-V2 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf GestaltLabs/Ornstein-3.5-9B-V2:BF16
# Run inference directly in the terminal:
llama-cli -hf GestaltLabs/Ornstein-3.5-9B-V2:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf GestaltLabs/Ornstein-3.5-9B-V2:BF16
# Run inference directly in the terminal:
llama-cli -hf GestaltLabs/Ornstein-3.5-9B-V2:BF16

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 GestaltLabs/Ornstein-3.5-9B-V2:BF16
# Run inference directly in the terminal:
./llama-cli -hf GestaltLabs/Ornstein-3.5-9B-V2:BF16

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 GestaltLabs/Ornstein-3.5-9B-V2:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GestaltLabs/Ornstein-3.5-9B-V2:BF16

Use Docker

docker model run hf.co/GestaltLabs/Ornstein-3.5-9B-V2:BF16

LM Studio
Jan

vLLM

How to use GestaltLabs/Ornstein-3.5-9B-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GestaltLabs/Ornstein-3.5-9B-V2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GestaltLabs/Ornstein-3.5-9B-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GestaltLabs/Ornstein-3.5-9B-V2:BF16

SGLang

How to use GestaltLabs/Ornstein-3.5-9B-V2 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 "GestaltLabs/Ornstein-3.5-9B-V2" \
    --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": "GestaltLabs/Ornstein-3.5-9B-V2",
		"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 "GestaltLabs/Ornstein-3.5-9B-V2" \
        --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": "GestaltLabs/Ornstein-3.5-9B-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use GestaltLabs/Ornstein-3.5-9B-V2 with Ollama:
```
ollama run hf.co/GestaltLabs/Ornstein-3.5-9B-V2:BF16
```

Unsloth Studio

How to use GestaltLabs/Ornstein-3.5-9B-V2 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 GestaltLabs/Ornstein-3.5-9B-V2 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 GestaltLabs/Ornstein-3.5-9B-V2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GestaltLabs/Ornstein-3.5-9B-V2 to start chatting

How to use GestaltLabs/Ornstein-3.5-9B-V2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf GestaltLabs/Ornstein-3.5-9B-V2:BF16

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": "GestaltLabs/Ornstein-3.5-9B-V2:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use GestaltLabs/Ornstein-3.5-9B-V2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf GestaltLabs/Ornstein-3.5-9B-V2:BF16

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 GestaltLabs/Ornstein-3.5-9B-V2:BF16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use GestaltLabs/Ornstein-3.5-9B-V2 with Docker Model Runner:
```
docker model run hf.co/GestaltLabs/Ornstein-3.5-9B-V2:BF16
```

Lemonade

How to use GestaltLabs/Ornstein-3.5-9B-V2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GestaltLabs/Ornstein-3.5-9B-V2:BF16

Run and chat with the model

lemonade run user.Ornstein-3.5-9B-V2-BF16

List all available models

lemonade list

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Ornstein 3.5 9B — V2

The reinforcement-learning post-training of Ornstein 3.5 9B V1.5 — the V2 the V1.5 card promised. Starting from the V1.5 supervised fine-tune, V2 adds preference optimization (DPO) and verifiable-reward reinforcement learning (GRPO on math RLVR). The base model holds the knowledge; V1.5 shaped how it thinks; V2 sharpens it under reward — pushing graduate-level science (GPQA) and multi-step reasoning to the GBS-200 ceiling. Like V1.5, V2 keeps the native vision tower (image/video input via the bundled mmproj) and the multi-token-prediction (MTP) head for speculative decoding.

Benchmarks

Evaluated on the Gestalt Benchmark Suite (GBS, STANDARD-200) — a held-out, contamination-controlled reasoning + coding suite — paired on identical items with greedy decoding. The Qwen3.5-9B-Base and Ornstein V1.5 columns are the published references.

	Qwen3.5-9B-Base	Ornstein V1.5	Ornstein V2
Overall	0.725	0.850	0.825
Reasoning	0.68	0.90	1.00
GPQA (graduate-level science)	0.36	0.80	1.00
Coding	0.77	0.80	0.65

On this pod's fresh, same-seed GBS-200 run, V2 matched V1.5 overall (0.825 vs 0.825) while lifting reasoning to 1.00 and GPQA to 1.00 — both at the suite ceiling and far above the Qwen3.5-9B-Base (0.68 reasoning, 0.36 GPQA). The RL run traded some coding (0.80 → 0.65); a coding-focused variant is planned as a follow-up.

Release line

V1 — initial reasoning fine-tune.
V1.5 — refined supervised fine-tune on quality-gated reasoning data.
V2 — this release — reinforcement-learning post-training (DPO + GRPO verifiable-reward RL) on V1.5.

Quantizations

GGUF (llama.cpp, text + vision mmproj): GestaltLabs/Ornstein-3.5-9B-V2-GGUF
bf16 GGUF (in this repo; embeds the MTP draft head for --spec-type draft-mtp): ornstein-v2-bf16.gguf
AWQ int4 (ModelOpt, TensorRT-LLM/vLLM): GestaltLabs/Ornstein-3.5-9B-V2-W4A16-AWQ
NVFP4 (ModelOpt, Blackwell-optimized): GestaltLabs/Ornstein-3.5-9B-V2-NVFP4

Support This Work

I'm a PhD student in visual neuroscience at the University of Toronto who also happens to spend way too much time fine-tuning, merging, and quantizing open-weight models on rented H100s and a local DGX Spark. All training compute is self-funded — balancing GPU costs against a student budget. If my uploads have been useful to you, consider buying a PhD student a coffee. It goes a long way toward keeping these experiments running.

Support on Ko-fi

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "GestaltLabs/Ornstein-3.5-9B-V2"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto")

messages = [{"role": "user", "content": "Derive the variance of a sum of two correlated random variables."}]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(inputs, max_new_tokens=1024)
print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))

Intended Use

Reasoning-heavy tasks, AI-research assistance, technical and scientific problem-solving, and general conversation.

Details

Developed by: DJLougen / GestaltLabs
Base model: GestaltLabs/Ornstein-3.5-9B-V1.5
Post-training: DPO preference optimization + GRPO verifiable-reward RL (math RLVR)
Parameters: ~9.65B
Precision: BF16
Format: ChatML (conversational)
License: Apache 2.0