Instructions to use SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF",
	filename="HivemindPreview-32B-BF16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_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 SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_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 SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_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 SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF:Q4_K_M

Use Docker

docker model run hf.co/SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_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": "SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF:Q4_K_M

Ollama
How to use SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF with Ollama:
```
ollama run hf.co/SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF:Q4_K_M
```

Unsloth Studio new

How to use SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_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 SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_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 SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF to start chatting

Pi new

How to use SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF:Q4_K_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": "SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_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 SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_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 SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF with Docker Model Runner:
```
docker model run hf.co/SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF:Q4_K_M
```

Lemonade

How to use SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF:Q4_K_M

Run and chat with the model

lemonade run user.HIVEMIND_PREVIEW_32B_-_GGUF-Q4_K_M

List all available models

lemonade list

GGUF QUANTIZATIONS FOR HIVELABSAI'S "hivemind-32b-preview"

This model was made with llama.cpp build 9181 using Bartowski's sample dataset for an importance matrix. The Q8_0, BF16, and F16 quantizations do not use any importance matrix.

As the original model is a preview release, these quantizations should be considered experimental, though functioning. I [SUPEROXIDES] am not endorsed or sponsored by Hive Labs.

ORIGINAL README.MD FOR HIVEMIND PREVIEW 32B:

Hivemind-32B-Preview

Hivemind-32B-Preview is a 32B-parameter model fine-tuned for multi-turn, emotionally attentive conversation in human-facing enterprise contexts. It is built on Qwen3-32B with a training set focused on conversational depth, emotional subtext, and sustained engagement across complex interpersonal scenarios.

Model Details

Parameters: 32B
Context length: 40,960 tokens
Precision: bfloat16
Base model: Qwen3-32B
License: Proprietary, subject to upstream Qwen license terms

Training

Hivemind-32B-Preview was fine-tuned for multi-turn, human-facing conversations involving ambiguity and emotional subtext. The training set was purpose-built from enterprise interaction data.

Intended Use

Hivemind-32B-Preview is designed for enterprise human-agent partnership contexts: customer support, coaching-style interactions, and similar conversational deployments where sustained emotional attentiveness matters.

Scope and Ongoing Work

Hivemind-32B-Preview is a preview release. As with any conversational model, it has scope boundaries we are actively refining:

It is not intended as a source of medical, legal, financial, or safety-critical advice, and should not be deployed in those contexts or as a replacement for professional human support.
Performance is strongest in standard conversational scenarios.

We welcome failure-case reports from researchers and deployment partners at contact@hivelabs.dev.

Usage

vLLM (recommended)

vllm serve HiveLabsAI/hivemind-32b-preview --dtype bfloat16

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "HiveLabsAI/hivemind-32b-preview"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="bfloat16",
    device_map="auto",
)

messages = [{"role": "user", "content": "Your message here"}]
inputs = tokenizer.apply_chat_template(
    messages, return_tensors="pt", add_generation_prompt=True
).to(model.device)
outputs = model.generate(
    inputs, max_new_tokens=2048, temperature=0.6, top_p=0.95, top_k=20
)
print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))

About

Hivemind is developed by Hive Labs. For research collaboration, deployment questions, or to report failure cases, contact contact@hivelabs.dev.

Downloads last month: 1,937

GGUF

Model size

33B params

Architecture

qwen3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for SUPEROXIDES/HIVEMIND_PREVIEW_32B_-_GGUF

Base model

Qwen/Qwen3-32B

Finetuned

HiveLabsAI/hivemind-32b-preview

Quantized

(1)

this model