Instructions to use AesSedai/GLM-5.3-Flash-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 AesSedai/GLM-5.3-Flash-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 AesSedai/GLM-5.3-Flash-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AesSedai/GLM-5.3-Flash-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 AesSedai/GLM-5.3-Flash-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AesSedai/GLM-5.3-Flash-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 AesSedai/GLM-5.3-Flash-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AesSedai/GLM-5.3-Flash-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 AesSedai/GLM-5.3-Flash-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AesSedai/GLM-5.3-Flash-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AesSedai/GLM-5.3-Flash-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use AesSedai/GLM-5.3-Flash-GGUF with Ollama:
```
ollama run hf.co/AesSedai/GLM-5.3-Flash-GGUF:Q4_K_M
```
Unsloth Desktop

How to use AesSedai/GLM-5.3-Flash-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AesSedai/GLM-5.3-Flash-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": "AesSedai/GLM-5.3-Flash-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AesSedai/GLM-5.3-Flash-GGUF with Docker Model Runner:
```
docker model run hf.co/AesSedai/GLM-5.3-Flash-GGUF:Q4_K_M
```

Lemonade

How to use AesSedai/GLM-5.3-Flash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AesSedai/GLM-5.3-Flash-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.GLM-5.3-Flash-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use AesSedai/GLM-5.3-Flash-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 AesSedai/GLM-5.3-Flash-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 AesSedai/GLM-5.3-Flash-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AesSedai/GLM-5.3-Flash-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AesSedai/GLM-5.3-Flash-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 "AesSedai/GLM-5.3-Flash-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"

Confused about the differences vs Unsloth GGUFs

by WetRat - opened Sep 10

Discussion

WetRat

Sep 10

Hi there! So, uhm, Unsloth’s GLM-5.3-Flash GGUFs appear to have been quantized from a mixed FP8/BF16 base model rather than the full weights.

Looking at your GGUFs, they require a different llama.cpp PR, and of course there are disparities in precision, like SSM weights being FP32 instead of Q8_0, and the differences around hc_attn_fn, and so on.

Let's say the model (Unsloth’s UD-Q5_K_XL) currently jumbles up the words in a language it doesn't officially support, but it's only in about 20% of its answers, with the remaining 80% being flawless - a native speaker level of quality. Would it be entirely hopeless to expect your Q5_K_M to mend the model's sudden fits of dyslexia? I just want to understand how the aforementioned disparities in precision correlate with the output quality. Genuinely feeling like a dumbass rn.

AesSedai

Owner Sep 13

Hi, honestly I can't really speak to the Unsloth variants because I've only quantized and run these that are compatible with Chronos's PR. I don't think I've seen reports of that kind of word jumbling, but there's been some mention of gremlins (aka, the Kimi-K2.6 era logic derps) but not like flat out word jumbles?

I'd say download and try it?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment