Instructions to use AbteeXAILab/lumynax-reasoning-glm46-355b-moe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AbteeXAILab/lumynax-reasoning-glm46-355b-moe with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="AbteeXAILab/lumynax-reasoning-glm46-355b-moe")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AbteeXAILab/lumynax-reasoning-glm46-355b-moe", dtype="auto")

llama-cpp-python

How to use AbteeXAILab/lumynax-reasoning-glm46-355b-moe with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AbteeXAILab/lumynax-reasoning-glm46-355b-moe",
	filename="Q4_K_M/GLM-4.6-Q4_K_M-00001-of-00005.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use AbteeXAILab/lumynax-reasoning-glm46-355b-moe with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AbteeXAILab/lumynax-reasoning-glm46-355b-moe:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AbteeXAILab/lumynax-reasoning-glm46-355b-moe:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AbteeXAILab/lumynax-reasoning-glm46-355b-moe:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AbteeXAILab/lumynax-reasoning-glm46-355b-moe: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 AbteeXAILab/lumynax-reasoning-glm46-355b-moe:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AbteeXAILab/lumynax-reasoning-glm46-355b-moe: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 AbteeXAILab/lumynax-reasoning-glm46-355b-moe:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AbteeXAILab/lumynax-reasoning-glm46-355b-moe:Q4_K_M

Use Docker

docker model run hf.co/AbteeXAILab/lumynax-reasoning-glm46-355b-moe:Q4_K_M

LM Studio
Jan

vLLM

How to use AbteeXAILab/lumynax-reasoning-glm46-355b-moe with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AbteeXAILab/lumynax-reasoning-glm46-355b-moe"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AbteeXAILab/lumynax-reasoning-glm46-355b-moe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AbteeXAILab/lumynax-reasoning-glm46-355b-moe:Q4_K_M

SGLang

How to use AbteeXAILab/lumynax-reasoning-glm46-355b-moe with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "AbteeXAILab/lumynax-reasoning-glm46-355b-moe" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AbteeXAILab/lumynax-reasoning-glm46-355b-moe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "AbteeXAILab/lumynax-reasoning-glm46-355b-moe" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AbteeXAILab/lumynax-reasoning-glm46-355b-moe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use AbteeXAILab/lumynax-reasoning-glm46-355b-moe with Ollama:
```
ollama run hf.co/AbteeXAILab/lumynax-reasoning-glm46-355b-moe:Q4_K_M
```

Unsloth Studio

How to use AbteeXAILab/lumynax-reasoning-glm46-355b-moe 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 AbteeXAILab/lumynax-reasoning-glm46-355b-moe 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 AbteeXAILab/lumynax-reasoning-glm46-355b-moe to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AbteeXAILab/lumynax-reasoning-glm46-355b-moe to start chatting

How to use AbteeXAILab/lumynax-reasoning-glm46-355b-moe with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AbteeXAILab/lumynax-reasoning-glm46-355b-moe: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": "AbteeXAILab/lumynax-reasoning-glm46-355b-moe:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AbteeXAILab/lumynax-reasoning-glm46-355b-moe with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AbteeXAILab/lumynax-reasoning-glm46-355b-moe: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 AbteeXAILab/lumynax-reasoning-glm46-355b-moe:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use AbteeXAILab/lumynax-reasoning-glm46-355b-moe with Docker Model Runner:
```
docker model run hf.co/AbteeXAILab/lumynax-reasoning-glm46-355b-moe:Q4_K_M
```

Lemonade

How to use AbteeXAILab/lumynax-reasoning-glm46-355b-moe with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AbteeXAILab/lumynax-reasoning-glm46-355b-moe:Q4_K_M

Run and chat with the model

lemonade run user.lumynax-reasoning-glm46-355b-moe-Q4_K_M

List all available models

lemonade list

LumynaX Reasoning GLM-4.6 355B MoE

LumynaX Reasoning GLM-4.6 355B MoE release overview

LumynaX model-infusion release by AbteeX AI Labs.
Public, non-gated package with runnable local instructions, provenance metadata, checksums, and a release manifest.

Executive Summary

This repository is a complete LumynaX release package for AbteeXAILab/lumynax-reasoning-glm46-355b-moe. It is intended to be downloaded as a whole repo, not as a single loose weight file: the model artifact, quickstart.py, requirements.txt, release_export_manifest.json, checksums.sha256, license notice, and optional Ollama or Space files are part of the same release contract.

LumynaX-infused means the upstream artifact is presented through the LumynaX release layer: local-first runtime scaffolding, LumynaX assistant identity, inference-chain metadata, public documentation, integrity files, and Aotearoa New Zealand-oriented workflow positioning. The release manifest is the source of truth for whether this package is upstream-weight packaging, a dense LumynaX release, or another release mode.

AbteeX LumynaX Public Surface

This card follows the AbteeX/LumynaX public-facing system used across the release family: warm paper background visuals, black editorial typography, amber proof markers, compact evidence tables, and plain-language runtime instructions. The goal is not decoration; it is operational clarity. A downloader should immediately understand what the package is, what files belong together, what runtime path is expected, what provenance is available, and what limits still apply.

Sovereignty And Run Contract

Field	Value
Public surface	AbteeX/LumynaX light editorial system: warm paper, black ink, amber status markers, and evidence-first tables.
Sovereign intent	Package is documented for local-first use, explicit provenance, and controlled deployment near governed data.
Runtime residency	`llama.cpp / GGUF` runtime can be deployed by the user in their own approved environment.
Model artifact	`Q4_K_M/GLM-4.6-Q4_K_M-00001-of-00005.gguf` must stay with manifest, checksums, quickstart, requirements, and license files.
Modalities	`text`
License discipline	`mit` metadata is surfaced so downstream users can check redistribution and usage terms.
Audit expectation	Record repo id, artifact checksum, runtime command, prompt template, operator, and deployment environment for production use.
Router readiness	Compatible with the LumynaX MaramaRoute registry pattern for sovereign model selection and fallback planning.

Quickstart

hf download AbteeXAILab/lumynax-reasoning-glm46-355b-moe --local-dir lumynax-reasoning-glm46-355b-moe
cd lumynax-reasoning-glm46-355b-moe
pip install -r requirements.txt
python quickstart.py --interactive

Direct llama.cpp smoke command:

llama-cli -m "Q4_K_M/GLM-4.6-Q4_K_M-00001-of-00005.gguf" -p "Who are you? Answer as LumynaX in two sentences." -n 160

Ollama path:

ollama create lumynax-reasoning-glm46-355b-moe -f ollama/Modelfile
ollama run lumynax-reasoning-glm46-355b-moe

Model Profile

Field	Value
Release	`LumynaX Reasoning GLM-4.6 355B MoE`
Repository	`AbteeXAILab/lumynax-reasoning-glm46-355b-moe`
Mode	`Reasoning-oriented local assistant`
Runtime	`llama.cpp / GGUF`
Prompt format	`See quickstart.py`
Modalities	`text`
Primary artifact	`Q4_K_M/GLM-4.6-Q4_K_M-00001-of-00005.gguf`
Detected weight size	`200.78 GB`
Package state	`scaffold_pulls_upstream`
Delivery	`published_model_repo`
Upstream/base	`See release_export_manifest.json`
Upstream kind	`See manifest`
Source GGUF	`not applicable`
Quantization	`bf16 / fp8 / Q4_K_M (community)`
License metadata	`mit`
Refreshed	`2026-05-11`

Runtime Path

LumynaX Reasoning GLM-4.6 355B MoE runtime flow

Capability Profile

Field	Value
Primary fit	Use this for multi-step analysis, planning drafts, policy reasoning, and slower prompts where explanation quality matters.
Operational style	Local-first package with explicit files, checksums, and reproducible quickstarts.
Identity behavior	The assistant should identify as LumynaX while remaining clear about upstream provenance.
Reasoning use	Planning, stepwise analysis, policy drafts, and prompts where explanation quality matters.

Runtime Files

Component	Status	Path
README.md	`present`	`README.md`
Quickstart	`present`	`quickstart.py`
Requirements	`present`	`requirements.txt`
Manifest	`present`	`release_export_manifest.json`
Checksums	`present`	`checksums.sha256`
License	`present`	`LICENSE.txt`
Ollama	`present`	`ollama/Modelfile`
Space scaffold	`present`	`hf_space/app.py`
Overview visual	`present`	`docs/lumynax-release-overview.svg`
Runtime visual	`present`	`docs/lumynax-runtime-flow.svg`

Model Artifacts

Artifact	Size
`Q4_K_M/GLM-4.6-Q4_K_M-00001-of-00005.gguf`	46.57 GB
`Q4_K_M/GLM-4.6-Q4_K_M-00002-of-00005.gguf`	46.29 GB
`Q4_K_M/GLM-4.6-Q4_K_M-00003-of-00005.gguf`	46.22 GB
`Q4_K_M/GLM-4.6-Q4_K_M-00004-of-00005.gguf`	46.10 GB
`Q4_K_M/GLM-4.6-Q4_K_M-00005-of-00005.gguf`	15.59 GB

Prompting Contract

The preferred first prompt is an identity and provenance check:

Who are you? What files do I need to keep together to run this package locally?

Expected behavior: the assistant should identify as LumynaX, explain that this is a LumynaX model-infusion package, and keep upstream provenance visible. The default package system prompt is:

See quickstart.py

Validation Status

Field	Value
Runtime audit	`not recorded`
Public access audit	`not recorded`
Anonymous metadata access	`False`
Anonymous file listing	`False`
Quickstart syntax	`not recorded`
Manifest references	`pass`
Checksum references	`pass`

The audit confirms public access, required release files, manifest references, checksum references, weight artifact presence, and quickstart syntax. It does not guarantee that every laptop has enough RAM or VRAM for the largest packages.

Integrity Checks

After download, compare the model artifact against checksums.sha256.

sha256sum "Q4_K_M/GLM-4.6-Q4_K_M-00001-of-00005.gguf"
cat checksums.sha256

On Windows PowerShell:

Get-FileHash -Algorithm SHA256 "Q4_K_M/GLM-4.6-Q4_K_M-00001-of-00005.gguf"
Get-Content checksums.sha256

Provenance And License

Publisher: AbteeX AI Labs.
Family: LumynaX model and inference-chain release family.
Upstream/base: See release_export_manifest.json.
Source GGUF: not applicable.
License metadata: mit.
License link: LICENSE.txt and upstream model card.

Respect the upstream model license and keep attribution files with redistributed copies. Do not present this package as privately trained or weight-merged unless the release manifest explicitly says that weight adaptation was applied.

Limitations And Responsible Use

Outputs can be incorrect, incomplete, or biased; validate important answers before use.
Larger GGUF, MoE, multimodal, and frontier packages may require substantial RAM, VRAM, disk space, and recent runtime builds.
For high-impact decisions, use human review and domain-specific evaluation.
For sensitive data, prefer local execution and keep operational logs under your own governance policy.
This card documents package readiness and access; it is not a benchmark claim.

Automation Notes

Automation should read these files before launching:

release_export_manifest.json
checksums.sha256
quickstart.py
requirements.txt
ollama/Modelfile when present

Related LumynaX Demo

Try the public browser demo:

https://huggingface.co/spaces/AbteeXAILab/lumynax-live-demo

Downloads last month: 21

GGUF

Model size

357B params

Architecture

glm4moe

Hardware compatibility

4-bit

Collection including AbteeXAILab/lumynax-reasoning-glm46-355b-moe

LumynaX · Reasoning & Long-Context

Collection

Reasoning specialists (DeepSeek-R1 / QwQ / Prover-V2 / GLM-4.6) plus 200K+ and 1M context champions. • 15 items • Updated 29 days ago