Instructions to use Outlier-Ai/Outlier-Max-32B-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 Outlier-Ai/Outlier-Max-32B-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 Outlier-Ai/Outlier-Max-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Outlier-Ai/Outlier-Max-32B-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 Outlier-Ai/Outlier-Max-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Outlier-Ai/Outlier-Max-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 Outlier-Ai/Outlier-Max-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Outlier-Ai/Outlier-Max-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 Outlier-Ai/Outlier-Max-32B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Outlier-Ai/Outlier-Max-32B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Outlier-Ai/Outlier-Max-32B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Outlier-Ai/Outlier-Max-32B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Outlier-Ai/Outlier-Max-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": "Outlier-Ai/Outlier-Max-32B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Outlier-Ai/Outlier-Max-32B-GGUF:Q4_K_M

Ollama
How to use Outlier-Ai/Outlier-Max-32B-GGUF with Ollama:
```
ollama run hf.co/Outlier-Ai/Outlier-Max-32B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Outlier-Ai/Outlier-Max-32B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Outlier-Ai/Outlier-Max-32B-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": "Outlier-Ai/Outlier-Max-32B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Outlier-Ai/Outlier-Max-32B-GGUF with Docker Model Runner:
```
docker model run hf.co/Outlier-Ai/Outlier-Max-32B-GGUF:Q4_K_M
```

Lemonade

How to use Outlier-Ai/Outlier-Max-32B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Outlier-Ai/Outlier-Max-32B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Outlier-Max-32B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Outlier-Ai/Outlier-Max-32B-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 Outlier-Ai/Outlier-Max-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 Outlier-Ai/Outlier-Max-32B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Outlier-Ai/Outlier-Max-32B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Outlier-Ai/Outlier-Max-32B-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 "Outlier-Ai/Outlier-Max-32B-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"

ur-dad-matt commited on May 5

Commit

072095d

verified ·

1 Parent(s): be9b1c7

docs(card): SEO + cross-link refresh (HF-DISCOVERABILITY-001)

Browse files

Files changed (1) hide show

README.md +15 -86

README.md CHANGED Viewed

@@ -67,99 +67,28 @@ widget:
     content: Summarize the differences between 4-bit and 8-bit quantization in two
       short paragraphs.
 ---
-> # ⚠️ Pre-v1.8 build — see [Outlier-Ai org](https://huggingface.co/Outlier-Ai) for current MLX 4-bit lineup
->
-> This is a **Max (deferred to v1.9+ — see Plus tier on Outlier-Ai org) GGUF** build from a pre-v1.8 era. The current Outlier app (v1.8+) ships **MLX 4-bit** versions optimized for Apple Silicon — much faster than GGUF on Mac.
->
-> | Want | Use |
-> |---|---|
-> | **Run on macOS** (any M-series Mac) | [Outlier-Ai (MLX 4-bit lineup)](https://huggingface.co/Outlier-Ai) |
-> | **Run on Windows / Linux** | This GGUF still works with [llama.cpp](https://github.com/ggerganov/llama.cpp), [Ollama](https://ollama.ai), [LM Studio](https://lmstudio.ai), [Jan](https://jan.ai) |
->
-> [📥 Download the Outlier desktop app](https://outlier.host)
----
-# Outlier Max 32B (GGUF)
-Cross-platform build for llama.cpp, Ollama, LM Studio, and Jan. Runs on macOS, Windows, and
-Linux. Multiple quant levels included so you can pick by RAM budget.
-## Quick facts
-- **Formats included:** Q4_K_M, Q5_K_M, Q8_0
-- **Frozen base:** [Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct)
-- **License:** Apache 2.0
-- **Runtime:** llama.cpp, Ollama, LM Studio, Jan, any GGUF consumer
-## Quickstart (Ollama)
-```bash
-ollama run hf.co/Outlier-Ai/Outlier-Max-32B-GGUF:Q4_K_M
-```
-## Quickstart (llama.cpp)
-```bash
-./llama-cli \
-  -m Outlier-Ai/Outlier-Max-32B-GGUF/model-Q4_K_M.gguf \
-  -p "Explain 4-bit quantization in one paragraph." \
-  -n 256
-```
-## Quant picker
-| Quant | Recommended for |
-|---|---|
-| Q4_K_M | most users, laptops with 8 GB plus of free RAM |
-| Q5_K_M | better quality trade, 12 GB plus free RAM |
-| Q8_0 | highest quality, 24 GB plus free RAM |
-## Related
-- **Outlier organization:** [Outlier-Ai](https://huggingface.co/Outlier-Ai)
-- **Consumer Edition collection:** [Outlier-Ai/outlier-consumer-edition-69e2fb4a0df119ea1747275e](https://huggingface.co/collections/Outlier-Ai/outlier-consumer-edition-69e2fb4a0df119ea1747275e)
-- **Research collection:** [Outlier-Ai/outlier-research-69e2fb3a71984614b3c7a279](https://huggingface.co/collections/Outlier-Ai/outlier-research-69e2fb3a71984614b3c7a279)
-- **Server V3.2 collection:** [Outlier-Ai/outlier-server-v32-69e2fb4b71984614b3c7a4a3](https://huggingface.co/collections/Outlier-Ai/outlier-server-v32-69e2fb4b71984614b3c7a4a3)
-- **Desktop app:** [https://outlier.host](https://outlier.host)
-- **Founders lifetime ($200, 500-seat cap):** [https://buy.polar.sh/polar_cl_mJfYZsEpEMDcYrgxzvTdnahSeSQNq1UYLqV0l08CUhW](https://buy.polar.sh/polar_cl_mJfYZsEpEMDcYrgxzvTdnahSeSQNq1UYLqV0l08CUhW)
-- **Discord:** [discord.gg/Hapennmdn9](https://discord.gg/Hapennmdn9)
-## What is Outlier?
-Outlier is a Mac-native, offline by default AI platform. One desktop app, a curated model library,
-Bring-Your-Own-Model support, projects with codebase indexing, a 9-tool coding agent, an
-artifacts panel, SQLite memory, and an OpenAI-compatible local API - all Apache 2.0,
-all local, no cloud round-trip, no per-token billing.
-- **Desktop app:** [https://outlier.host](https://outlier.host)
-- **Founders lifetime (500-seat cap, $200 one-time):** [support Outlier](https://buy.polar.sh/polar_cl_mJfYZsEpEMDcYrgxzvTdnahSeSQNq1UYLqV0l08CUhW)
-- **Discord:** [discord.gg/Hapennmdn9](https://discord.gg/Hapennmdn9)
-- **Org:** [huggingface.co/Outlier-Ai](https://huggingface.co/Outlier-Ai)
-Built solo in Grand Rapids, Michigan. 19 days to 35+ HF repos and 8,305 downloads, under
-$1,200 in compute spend. Mission: a local AI model that codes as well as the cloud flagships,
-funded by users who want it - not investors who need exits.
-## Known limits
-- Quant level affects quality. Q4_K_M is the recommended default; Q5/Q8 trade size for
-  quality.
-- Speed depends heavily on RAM bandwidth and CPU. llama.cpp picks the best kernel for your
-  hardware automatically.
-- English-tuned. Multilingual behavior inherits the base model directly.
-## Attribution
-Base model by the **Qwen team at Alibaba**, Apache 2.0. Outlier contributes GGUF packaging.
-Capability credit for the base belongs to upstream.
-- Qwen team: [qwenlm.github.io](https://qwenlm.github.io/)
-- Qwen 2.5 release: [arxiv.org/abs/2412.15115](https://arxiv.org/abs/2412.15115)
-## License and citation
-Apache 2.0 throughout. Base weights under Apache 2.0 from the Qwen team; GGUF quants
-contributed by Outlier-Ai and released under the same terms.

     content: Summarize the differences between 4-bit and 8-bit quantization in two
       short paragraphs.
 ---
+> **Superseded.** This repo is a research artifact from an earlier Outlier lineage and is no longer the recommended download. The current shipping tier is at **[outlier.host](https://outlier.host/?utm_source=hf&utm_medium=modelcard&utm_campaign=outlier_max_32b_gguf)**.
+# Outlier-Max-32B (GGUF)
+This repo predates the v1.8 Outlier lineup. It is preserved here for reproducibility and historical reference, not as a production recommendation.
+## What replaced it
+Current shipping tiers (see Outlier app v1.8+):
+- [Outlier Nano 4B — current entry tier](https://huggingface.co/Outlier-Ai/Outlier-Nano-4B-MLX-4bit)
+- [Outlier Core 27B — current default tier](https://huggingface.co/Outlier-Ai/Outlier-Core-27B-MLX-4bit)
+- [Outlier Vision 35B-A3B — current multimodal tier](https://huggingface.co/Outlier-Ai/Outlier-Vision-35B-A3B-MLX-4bit)
+- [DeepSeek-R1-Distill-Qwen-7B — popular reasoning model](https://huggingface.co/Outlier-Ai/DeepSeek-R1-Distill-Qwen-7B-MLX-4bit)
+- [Qwen3-Coder-30B-A3B — popular coding model](https://huggingface.co/Outlier-Ai/Qwen3-Coder-30B-A3B-Instruct-MLX-4bit)
+For the latest verified benchmarks and downloads, visit **[outlier.host](https://outlier.host/?utm_source=hf&utm_medium=modelcard&utm_campaign=outlier_max_32b_gguf)**.
+## Original notes
+This was a research / preview artifact. It may contain experimental adapters, overlays, or quantization variants that did not graduate into the shipping product. Treat any technical claims in earlier revisions of this card as provisional.
+## License
+See YAML frontmatter above. Original license terms preserved.