Instructions to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF 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 GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-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 GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-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 GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_M

Use Docker

docker model run hf.co/GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-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": "GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_M

Ollama
How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF with Ollama:
```
ollama run hf.co/GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_M
```
Unsloth Desktop

How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF with Docker Model Runner:
```
docker model run hf.co/GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_M
```

Lemonade

How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Ornstein3.6-35B-A3B-RYS-SABER-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_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 GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_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 "GestaltLabs/Ornstein3.6-35B-A3B-RYS-SABER-GGUF:Q4_K_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"

crashed

by androidli - opened Apr 17

Discussion

androidli

Apr 17

Total : 20029.33, 2406.81, 22436.14 MiB
Memory required for model tensors + cache: 22834 MiB
Memory available on all devices - compute: 22799 MiB
llm_load_tensors: ggml ctx size = 0.61 MiB
llama_model_load: error loading model: check_tensor_dims: tensor 'blk.11.attn_q.weight' not found
llama_model_load_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model 'models/DJLougen/Ornstein3.6-35B-A3B-RYS-SABER-GGUF/Ornstein3.6-35B-A3B-RYS-SABER-Q4_K_M.gguf'
ERR [ load_model] unable to load model | tid="127779220193280" timestamp=1776405417 model="models/DJLougen/Ornstein3.6-35B-A3B-RYS-SABER-GGUF/Ornstein3.6-35B-A3B-RYS-SABER-Q4_K_M.gguf"
free(): invalid pointer
Aborted (core dumped)

guiperpt

Apr 17

Same thing here with the Q4_K_S version.

load_tensors: loading model tensors, this can take a while... (mmap = false, direct_io = false)
llama_model_load: error loading model: missing tensor 'blk.11.attn_q.weight'
llama_model_load_from_file_impl: failed to load model

PredragR

Apr 17

•

edited Apr 17

I can confirm this on latest llama.cpp with Q4_K_M. Everything seems normal on load up to this line where it crashes:
'''
...
create_tensor: loading tensor blk.11.attn_qkv.weight
llama_model_load: error loading model: check_tensor_dims: tensor 'blk.11.attn_qkv.weight' has wrong shape; expected 2048, 9216, got 2048, 8192, 1, 1
llama_model_load_from_file_impl: failed to load model
...
'''

EDIT: Same happens with Q5_K_M. Shame, I really want to try this one out!
EDIT 2: I made my own quant through hf - Q5_K_M from the DJLougen/Ornstein3.6-35B-A3B-RYS-SABER, still not working - the problem is that model, or at the top @DJLougen .

ajs410

Apr 17

•

edited Apr 20

I'm having the same problem as the others with ollama. Using Q8
source=server.go:1218 msg="llm load error: failed to initialize model: qwen3next: layer 12 missing attn_qkv/attn_gate projections"

Ornstein3.6-35B-A3B-RYS-GGUF also fails, however Ornstein3.6-35B-A3B-SABER-GGUF succeeds.

EDIT: the instructions say we need a special fork of llama.cpp

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment