Instructions to use BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-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 BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-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 BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S
# Run inference directly in the terminal:
llama cli -hf BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S
# Run inference directly in the terminal:
llama cli -hf BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S

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 BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S
# Run inference directly in the terminal:
./build/bin/llama cli -hf BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S

Use Docker

docker model run hf.co/BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S

Llama new
LM Studio
Jan

vLLM

How to use BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-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": "BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S

Ollama
How to use BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF with Ollama:
```
ollama run hf.co/BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S
```
Unsloth Desktop

How to use BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S

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": "BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S
```

Lemonade

How to use BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S

Run and chat with the model

lemonade run user.GLM-5.3-Flash-GSQ-RCO-MTP-GGUF-IQ3_S

List all available models

lemonade list

Hermes Agent

How to use BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-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 BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S

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 BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S

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 "BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF:IQ3_S" \
  --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"

This is a simple modification of pfeifferj/GLM-5.3-Flash-GSQ-RCO-GGUF we made for our needs. Hope that you might find it useful too.

The quantized MTP Q4_K_M nextn layer from unsloth/GLM-5.3-Flash-GGUF has been grafted into the GSQ-RCO IQ3_S quantization of the original model. It is running in production on a single AMD Instinct MI210 GPU, using llama.cpp v0.7.0.

GSQ-RCO quantization

Credits should also go to the Deep Algorithms and Systems Lab (ISTA/DASLab), Institute of Science and Technology Austria that developed GSQ-RCO quantization method used to build the model.

GSQ provides accurate low-bit scalar quantization of each tensor at a given quantization type; RCO assigns the per-tensor quantization types under a size budget. Together they yield a non-uniform GGUF at the requested size.

Method	Description
GSQ (Gumbel-Softmax Quantization, paper, code)	Post-training scalar quantization that jointly learns the per-coordinate grid assignments and the per-group scales via a Gumbel-Softmax relaxation. GSQ closes most of the gap between scalar and vector quantization at 2 to 3 bits while remaining deployable in standard scalar formats such as GGUF.
RCO (Riemannian Constrained Optimization, paper, code)	Assigns one of K quantization types to each of N tensors under a total size budget. The budget constraint is reformulated as a smooth Riemannian manifold in logit space, which permits gradient-based optimization directly on the task loss while enforcing the budget exactly, without constraint-specific hyperparameter tuning.

Performance

On our setup the model is roughly 15% faster than unsloth/GLM-5.3-Flash-GGUF:UD-Q4_K_XL.

BioDec GSQ-RCO:IQ3_S vs. Unsloth Q4_K_M.

Derived using llama-benchy, AMD MI210, single GPU. draft_n_max=1

ctx len	ctx_tg (t/s)	tg32 (t/s)
16k	19.17 / 17.24 = +11.2%	20.15 / 17.42 = +15.7%
32k	17.77 / 15.39 = +15.5%	16.95 / 14.85 = +14.2%
64k	14.66 / 13.57 = +8.0%	14.96 / 12.65 = +18.3%

This model contains the IQ3_S quantization only, since the GSQ-RCO IQ3_XXS version of the model proved unstable in agentic workflows, showing a tendency to loop that is absent in the larger quantization.

Our llama.cpp configuration

The stanza from the model.ini file

[BioDec/GLM-5.3-Flash-GSQ-RCO-MTP-GGUF]
;alias = "GLM-5.3-Flash"
split-mode = layer
ctx-size = 163840
parallel = 1
fit-target = 2048
;mmproj-offload = off
;
cache-type-k = q8_0
cache-type-v = q8_0
kv-unified = on
;
batch-size = 4096 
ubatch-size = 2048
; 
spec-type = draft-mtp
spec-draft-n-max = 1
load-mode = none

On our machine, spec-draft-n-max >1 did not provide measurable advantage despite acceptance being good. The same held true for DFlash2 speculative models.