Instructions to use mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF",
	filename="Olmo-3.1-32B-Instruct-SFT.i1-IQ1_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-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 mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-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 mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-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 mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-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 mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-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 mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-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 mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF to start chatting

How to use mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-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": "mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-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 mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-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 mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Olmo-3.1-32B-Instruct-SFT-i1-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on Jan 7

Commit

a3771e6

verified ·

1 Parent(s): 3a83414

auto-patch README.md

Browse files

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -40,11 +40,14 @@ more details, including on how to concatenate multi-part files.
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
 | [GGUF](https://huggingface.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF/resolve/main/Olmo-3.1-32B-Instruct-SFT.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |
 | [GGUF](https://huggingface.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF/resolve/main/Olmo-3.1-32B-Instruct-SFT.i1-Q2_K.gguf) | i1-Q2_K | 12.1 | IQ3_XXS probably better |
 | [GGUF](https://huggingface.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF/resolve/main/Olmo-3.1-32B-Instruct-SFT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.6 | lower quality |
 | [GGUF](https://huggingface.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF/resolve/main/Olmo-3.1-32B-Instruct-SFT.i1-IQ3_M.gguf) | i1-IQ3_M | 14.6 |  |
 | [GGUF](https://huggingface.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF/resolve/main/Olmo-3.1-32B-Instruct-SFT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 15.7 | IQ3_S probably better |
 | [GGUF](https://huggingface.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF/resolve/main/Olmo-3.1-32B-Instruct-SFT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.5 | optimal size/speed/quality |
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):

 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
 | [GGUF](https://huggingface.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF/resolve/main/Olmo-3.1-32B-Instruct-SFT.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |
+| [GGUF](https://huggingface.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF/resolve/main/Olmo-3.1-32B-Instruct-SFT.i1-IQ2_M.gguf) | i1-IQ2_M | 11.1 |  |
 | [GGUF](https://huggingface.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF/resolve/main/Olmo-3.1-32B-Instruct-SFT.i1-Q2_K.gguf) | i1-Q2_K | 12.1 | IQ3_XXS probably better |
 | [GGUF](https://huggingface.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF/resolve/main/Olmo-3.1-32B-Instruct-SFT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.6 | lower quality |
 | [GGUF](https://huggingface.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF/resolve/main/Olmo-3.1-32B-Instruct-SFT.i1-IQ3_M.gguf) | i1-IQ3_M | 14.6 |  |
 | [GGUF](https://huggingface.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF/resolve/main/Olmo-3.1-32B-Instruct-SFT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 15.7 | IQ3_S probably better |
 | [GGUF](https://huggingface.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF/resolve/main/Olmo-3.1-32B-Instruct-SFT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.5 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF/resolve/main/Olmo-3.1-32B-Instruct-SFT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.6 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Olmo-3.1-32B-Instruct-SFT-i1-GGUF/resolve/main/Olmo-3.1-32B-Instruct-SFT.i1-Q6_K.gguf) | i1-Q6_K | 26.5 | practically like static Q6_K |
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):