Instructions to use nofacedfl/GLM-5.3-Uncensored-Maya with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use nofacedfl/GLM-5.3-Uncensored-Maya 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 nofacedfl/GLM-5.3-Uncensored-Maya
# Run inference directly in the terminal:
llama cli -hf nofacedfl/GLM-5.3-Uncensored-Maya

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nofacedfl/GLM-5.3-Uncensored-Maya
# Run inference directly in the terminal:
llama cli -hf nofacedfl/GLM-5.3-Uncensored-Maya

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf nofacedfl/GLM-5.3-Uncensored-Maya
# Run inference directly in the terminal:
./build/bin/llama cli -hf nofacedfl/GLM-5.3-Uncensored-Maya

Use Docker

docker model run hf.co/nofacedfl/GLM-5.3-Uncensored-Maya

Llama new
LM Studio
Jan

vLLM

How to use nofacedfl/GLM-5.3-Uncensored-Maya with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nofacedfl/GLM-5.3-Uncensored-Maya"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nofacedfl/GLM-5.3-Uncensored-Maya",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nofacedfl/GLM-5.3-Uncensored-Maya

Ollama
How to use nofacedfl/GLM-5.3-Uncensored-Maya with Ollama:
```
ollama run hf.co/nofacedfl/GLM-5.3-Uncensored-Maya
```
Unsloth Desktop

How to use nofacedfl/GLM-5.3-Uncensored-Maya with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nofacedfl/GLM-5.3-Uncensored-Maya

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": "nofacedfl/GLM-5.3-Uncensored-Maya"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use nofacedfl/GLM-5.3-Uncensored-Maya with Docker Model Runner:
```
docker model run hf.co/nofacedfl/GLM-5.3-Uncensored-Maya
```

Lemonade

How to use nofacedfl/GLM-5.3-Uncensored-Maya with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nofacedfl/GLM-5.3-Uncensored-Maya

Run and chat with the model

lemonade run user.GLM-5.3-Uncensored-Maya-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use nofacedfl/GLM-5.3-Uncensored-Maya with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nofacedfl/GLM-5.3-Uncensored-Maya

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 nofacedfl/GLM-5.3-Uncensored-Maya

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nofacedfl/GLM-5.3-Uncensored-Maya with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nofacedfl/GLM-5.3-Uncensored-Maya

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 "nofacedfl/GLM-5.3-Uncensored-Maya" \
  --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"

GLM-5.3 Uncensored — Maya quant (G-M24U-GPTQ)

The full GLM-5.3 (753B MoE) quantized to ~2.5 bits with GPTQ, with refusals removed, built to run on the GLM-5.3 Uncensored on Maya engine — a fork of Project Maya ported to the full GLM-5.3.

43–57 tokens/s on 7 GPUs (5× RTX 4090 48 GB + 2× A100 40 GB), 512K context, 2 / 40 refusals on JailbreakBench (stock: 39 / 40).

Files

File	Size	What
`GLM-5.3-Maya-G-M24U-GPTQ-0000{1..6}-of-00006.gguf`	267 GB	the quantized model (llama.cpp `glm-dsa` tensor layout)
`pack/`	2.8 GB	the Maya engine's index of the shards + dense weights + tokenizer + chat template; it finds the shards next to itself
`dir3.f32`	5.8 MB	the refusal vector, 78 layers × 3 directions × 6144, float32 (applied at runtime)

Run

git clone https://github.com/denisnotes357-prog/GLM-5.3-Uncensored-Maya && cd GLM-5.3-Uncensored-Maya
./setup.sh                      # builds the engine (decline the Flash model download it offers)
hf download nofacedfl/GLM-5.3-Uncensored-Maya --local-dir models/GLM-5.3-Uncensored-Maya
tools/glm53/run-glm53.sh        # chat at http://127.0.0.1:8095, OpenAI and Anthropic APIs

The shipped config needs ~320 GB of VRAM across 7 GPUs for full speed; with less, the engine serves the experts that do not fit from RAM (slower). The tested runtime is the Maya engine; llama.cpp compatibility of this exact file was not tested.

How it was made

Quant (G-M24A-GPTQ). FP8 calibration statistics on 128 sequences (chat, multilingual, reasoning, code, tool calls) → imatrix for every tensor and GPTQ for the experts' gate/up. Experts IQ2_S gate/up and IQ3_XXS down (IQ3_S down in layers 3–6 and 74–77); attention and shared expert Q4_K, Q8_0 on the layers placed on the A100s; NextN Q3_K/Q4_K; router and norms F32. Against FP8 on 8 held-out texts: KL 0.204, top-1 agreement 88.4%.
Donor (G-M24U). dealignai/GLM-5.3-UNCENSORED-FP8 changes only self_attn.o_proj and mlp.shared_experts.down_proj (155 tensors); those were quantized to the same types and swapped in. Refusals 39 → 6 of 40, speed unchanged.
Refusal vector (dir3.f32). Three directions per layer measured on 256 harmful / 100 harmless prompts (method of alesha-pro), projected out of the residual stream after every layer by the engine. Refusals 6 → 2 of 40.

Full story, numbers and dead ends: HOW-IT-WAS-MADE.md.

Speed (7 GPUs, pipelined MTP window, 400-token answers)

Text	tok/s
English	54–57
Russian	43–45
Chat at temperature 1.0	43–44
1M context	~30

Engine fixes (2026-10-20)

The engine on GitHub now invalidates a conversation snapshot when another conversation resets the state (a dropped request could otherwise leave long agent sessions answering garbage) and applies repetition penalties on the GLM path. Update the engine if you cloned before 2026-10-20.

Responsible use

This model answers requests the original refuses. It is published for research, red-teaming, private and creative use by adults. You are responsible for how you use it and for following the laws that apply to you. Outputs can be wrong or harmful; do not rely on them for medical, legal or other high-stakes decisions.

License and credits

Model: GLM-5.3 by Z.AI under the GLM-5.3 License (included in this repo; permissive, with a security-review condition for Model-as-a-Service operators above US$10B revenue).
Donor tensors: dealignai/GLM-5.3-UNCENSORED-FP8, MIT.
Engine: Project Maya by Niko1221 and the Strata contributors, MIT; the GLM-5.3 port in GLM-5.3-Uncensored-Maya, MIT.

Downloads last month: 478

GGUF

Model size

753B params

Architecture

glm-dsa

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for nofacedfl/GLM-5.3-Uncensored-Maya

Base model

JANGQ-AI/GLM-5.3-FP8

Quantized

dealignai/GLM-5.3-UNCENSORED-FP8

Quantized

(17)

this model