Instructions to use GEHIRNS/magi-beta-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use GEHIRNS/magi-beta-1 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 GEHIRNS/magi-beta-1
# Run inference directly in the terminal:
llama cli -hf GEHIRNS/magi-beta-1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GEHIRNS/magi-beta-1
# Run inference directly in the terminal:
llama cli -hf GEHIRNS/magi-beta-1

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 GEHIRNS/magi-beta-1
# Run inference directly in the terminal:
./llama-cli -hf GEHIRNS/magi-beta-1

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 GEHIRNS/magi-beta-1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GEHIRNS/magi-beta-1

Use Docker

docker model run hf.co/GEHIRNS/magi-beta-1

LM Studio
Jan

vLLM

How to use GEHIRNS/magi-beta-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GEHIRNS/magi-beta-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GEHIRNS/magi-beta-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GEHIRNS/magi-beta-1

Ollama
How to use GEHIRNS/magi-beta-1 with Ollama:
```
ollama run hf.co/GEHIRNS/magi-beta-1
```
Unsloth Desktop

How to use GEHIRNS/magi-beta-1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GEHIRNS/magi-beta-1

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": "GEHIRNS/magi-beta-1"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use GEHIRNS/magi-beta-1 with Docker Model Runner:
```
docker model run hf.co/GEHIRNS/magi-beta-1
```

Lemonade

How to use GEHIRNS/magi-beta-1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GEHIRNS/magi-beta-1

Run and chat with the model

lemonade run user.magi-beta-1-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use GEHIRNS/magi-beta-1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GEHIRNS/magi-beta-1

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 GEHIRNS/magi-beta-1

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use GEHIRNS/magi-beta-1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GEHIRNS/magi-beta-1

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 "GEHIRNS/magi-beta-1" \
  --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"

Paper: Where the Bits Go (GEHIRNS, 2026), in preparation

Introduction

An alternative to magi-1.0 that spends extra bits on attention. It is published so the comparison can be reproduced. For use, take magi-1.0, which is smaller and scored slightly higher.

magi-beta-1 is Qwen/Qwen3.5-4B in a mixture of standard GGUF types. It differs from magi-1.0 in one place: the key, value and output projections of the 8 full-attention layers are stored at Q6_K instead of Q4_K. These are the most sensitive tensors in our measurements, yet the extra 0.030 GiB did not buy measurable accuracy (−0.65 points against magi-1.0, paired 95% interval −1.72 to +0.44). That supports the main finding: magi-1.0 already protects what matters. It involves no training and runs unmodified in llama.cpp and Ollama.

3.712 bits per weight all-in: 1.817 GiB of tensor data for 4,205,751,296 parameters (1.83 GiB file)
Text only: the vision projector of Qwen3.5-4B is not included.

Benchmarks

Same protocol as magi-1.0: one RTX 5070 (12 GB), 12 suites and 2,313 tasks, thinking on with a 4,096-token budget, greedy decoding, 32K context. Small numbers in the Ours columns are relative to BF16.

	Baselines			Ours
Benchmark	BF16 _{8.98 GiB}	Q4_K_M _{3.78 GiB}	Q2_K _{3.15 GiB}	magi-1.0 _{3.02 GiB}	magi-beta-1 _{3.07 GiB}
Efficiency
GPU memory at 32K (GiB)	8.98	3.78	3.15	3.02_{3.0× less}	3.07_{2.9× less}
Benchmark score	83.96%	84.14%	77.06%	81.30%_97%	80.65%_96%
Capability density	0.294	0.703	0.675	0.800_2.7×	0.771_2.6×
Decode speed (tok/s)	66.3	146.6	165.5	180.0_2.7×	181.0_2.7×
Traces ending in a loop	3.4%	3.3%	33.3%	9.4%	8.5%
Coding
HumanEval+	91.46	92.68	75.00	87.80	87.20
MBPP+	72.18	73.68	58.90	68.42	70.43
LiveCodeBench	35.33	35.33	15.33	24.67	20.00
Math
GSM8K	87.33	93.33	90.67	89.33	88.67
Science and Knowledge
ARC-Challenge	98.67	98.67	97.33	97.33	98.00
MMLU	84.50	82.50	74.00	82.00	81.50
OpenBookQA	95.00	96.50	93.00	96.00	95.50
SciQ	98.00	98.50	96.00	96.00	98.00
TruthfulQA	82.50	82.00	73.00	79.50	77.50
Commonsense
HellaSwag	75.50	72.00	71.50	72.00	68.00
WinoGrande	87.00	84.50	80.00	82.50	83.00
Tool Use
Function calling	100.00	100.00	100.00	100.00	100.00

Recipe

Tensor group	Type
FFN gate, up, down (all 32 layers); gated-attention output gate (24)	IQ3_XXS
DeltaNet `attn_qkv`, DeltaNet `ssm_out`, full-attention q, token embedding = tied head	Q4_K
Full-attention k, v, output (8 layers)	Q6_K
DeltaNet gates `ssm_alpha`, `ssm_beta`	Q8_0
Norms, convolution, A, Δt bias	F32

How to run

llama-server -m magi-beta-1.gguf -c 32768 --jinja
# or, with Ollama (0.40.3 verified to use the embedded template):
ollama create magi-beta-1 -f Modelfile && ollama run magi-beta-1

The 8-bit KV cache was not benchmarked for this model.

Limitations

The limitations of magi-1.0 apply. The model was evaluated on one benchmark, one runtime and one GPU, once per configuration. LiveCodeBench is the weakest suite (20.0% vs BF16's 35.3%). Text only. The name is ours, and this is not a fine-tune.