Instructions to use andreaborio/GLM-5.2-DS4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use andreaborio/GLM-5.2-DS4-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="andreaborio/GLM-5.2-DS4-GGUF",
	filename="GLM-5.2-DS4-ExpertMajor-v2-Q2_K.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 andreaborio/GLM-5.2-DS4-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 andreaborio/GLM-5.2-DS4-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf andreaborio/GLM-5.2-DS4-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf andreaborio/GLM-5.2-DS4-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf andreaborio/GLM-5.2-DS4-GGUF:Q2_K

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 andreaborio/GLM-5.2-DS4-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf andreaborio/GLM-5.2-DS4-GGUF:Q2_K

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 andreaborio/GLM-5.2-DS4-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf andreaborio/GLM-5.2-DS4-GGUF:Q2_K

Use Docker

docker model run hf.co/andreaborio/GLM-5.2-DS4-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use andreaborio/GLM-5.2-DS4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "andreaborio/GLM-5.2-DS4-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": "andreaborio/GLM-5.2-DS4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/andreaborio/GLM-5.2-DS4-GGUF:Q2_K

Ollama
How to use andreaborio/GLM-5.2-DS4-GGUF with Ollama:
```
ollama run hf.co/andreaborio/GLM-5.2-DS4-GGUF:Q2_K
```

Unsloth Studio

How to use andreaborio/GLM-5.2-DS4-GGUF 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 andreaborio/GLM-5.2-DS4-GGUF 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 andreaborio/GLM-5.2-DS4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for andreaborio/GLM-5.2-DS4-GGUF to start chatting

How to use andreaborio/GLM-5.2-DS4-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf andreaborio/GLM-5.2-DS4-GGUF:Q2_K

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": "andreaborio/GLM-5.2-DS4-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use andreaborio/GLM-5.2-DS4-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 andreaborio/GLM-5.2-DS4-GGUF:Q2_K

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 andreaborio/GLM-5.2-DS4-GGUF:Q2_K

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use andreaborio/GLM-5.2-DS4-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf andreaborio/GLM-5.2-DS4-GGUF:Q2_K

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 "andreaborio/GLM-5.2-DS4-GGUF:Q2_K" \
  --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"

Docker Model Runner
How to use andreaborio/GLM-5.2-DS4-GGUF with Docker Model Runner:
```
docker model run hf.co/andreaborio/GLM-5.2-DS4-GGUF:Q2_K
```

Lemonade

How to use andreaborio/GLM-5.2-DS4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull andreaborio/GLM-5.2-DS4-GGUF:Q2_K

Run and chat with the model

lemonade run user.GLM-5.2-DS4-GGUF-Q2_K

List all available models

lemonade list

GLM-5.2 DS4 GGUF releases

This is the definitive versioned GLM-5.2 model container for andreaborio/ds4. The current release is one qualified ExpertMajor v2 GGUF. The older chunked diagnostic artifact and its sidecar are retained only as historical experimental evidence.

Versions

Artifact	Status	Runtime
`GLM-5.2-DS4-ExpertMajor-v2-Q2_K.gguf`	Current	DS4 `main` at `57acfd4` or newer
`glm52-ds4-native-64g.gguf.part-000` through `part-005`	Legacy experimental diagnostic	Retired preview branch only; rejected by current DS4 inference
`sidecars/selected-hotlist-n32-pack2600/`	Legacy sidecar experiment	Retired; never selected by current DS4

DSBox and the root dsbox.json select only the single-file ExpertMajor v2 release. The legacy files remain available for reproducibility and historical links; they are not fallback formats. Current DS4 provides no compatibility path for the old chunked canonical layout or its sidecar.

The current file embeds the routed MoE bank once as ds4.expert_major.v2. It needs no sidecar, startup repack, or second copy of the routed weights. It is intentionally DS4-only: llama.cpp, MLX, Ollama, and other generic GGUF loaders cannot execute it.

Current artifact

Property	Value
Base model	`zai-org/GLM-5.2`
File	`GLM-5.2-DS4-ExpertMajor-v2-Q2_K.gguf`
Size	262,147,193,504 bytes (244.14 GiB)
SHA-256	`7f5017e3076e706c78f2a5322b035a9e2f6519c65ff5b6be8b2d91aeff61505d`
Container	GGUF v3 with one embedded `ds4.expert_major.v2` store
Tensor inventory	1,297 physical tensors; 1,524 logical tensors reconstructed by DS4
Routed geometry	76 routed layers, 256 experts per layer, top-8
Expert record	gate + up + down, 12,386,304 contiguous bytes
Routed payload	240,987,930,624 bytes (224.44 GiB)
Routed payload SHA-256	`122dcd3185037a3c0bcc8abab18ef61203ecfbfd2b25d02bd01e49c48778dfa9`
Qualified hardware	Apple Silicon Metal, at least 64 GiB unified memory

The v2 conversion changes routed-weight order and the GGUF tensor directory without requantizing values. Non-routed payloads are copied from the byte-identified source and routed weights are stored once.

Run with DS4

Use andreaborio/ds4 main at commit 57acfd408a3154851a0c59be432904300abb3b6c or a compatible descendant:

git clone https://github.com/andreaborio/ds4.git
cd ds4
make -j

./ds4 \
  -m /absolute/path/to/GLM-5.2-DS4-ExpertMajor-v2-Q2_K.gguf \
  --ctx 8192

The runtime automatically selects Metal, SSD residency, the GLM profile, contiguous-record expert reads, compact DSA KV, and the qualified cache policy. No Metal, SSD, cache, preload, full-layer, sidecar, or ExpertMajor flag is needed.

Measured performance

The release lane used an Apple M5 Pro with 64 GiB unified memory, local APFS storage, context 8192, an exact 288-token prompt, and 32 greedy output tokens:

Runtime arm	Prefill	Decode
Clean agent-friendly v2-only refactor	11.89 t/s	1.84 t/s
Post-unification v2-only gate	11.20 t/s	1.82 t/s
Earlier public-command gates	10.63-10.91 t/s	1.77-1.79 t/s
Prior rested-storage qualification, median	11.075 t/s	1.900 t/s

Every accepted arm produced the same deterministic continuation. These are bounded local measurements, not universal throughput guarantees.

The final compact-indexer correction was also exercised at 32K on the same 64 GiB host. The prose lane measured 44.73 t/s prefill, 1.87 t/s overall decode, and 472.624/621.302 ms TPOT p50/p95; p50 corresponds to about 2.12 t/s steady decode. A separate security/coding prompt measured 45.53/1.33 t/s because its expert-cache hit rate fell from 36.90% to 13.15%. Both runs completed with zero new swapout and exact retained evidence. The original baseline fails the 32K transition before logits, so this is a correctness qualification rather than a speedup claim.

Legacy experimental artifact

The retained diagnostic source reconstructs to glm52-ds4-native-64g.gguf, 262,147,189,920 bytes, SHA-256 99e18cf31620845f6ff8e08ec8074865b613a3684383fa53ebb93e77260d7dd5. It is stored as six part-000 through part-005 files with checksum manifests and reconstruct.sh. The optional 32,204,390,400-byte selected-hotlist sidecar is also historical. Neither layout is supported by current DS4 inference.

These files document the early CPU/preview and selected-hotlist bring-up that preceded the embedded ExpertMajor v2 store. Keep them for reproducibility; do not use their old startup commands with current main.

Limitations

Minimum qualified memory is 64 GiB unified memory.
One complete local ExpertMajor v2 file and Apple Metal SSD streaming are mandatory.
8K is the normal 64 GiB starting point and 32K is qualified but slow to test; no 65K/100K GLM claim is made because this release does not change attention, KV geometry, RoPE, or context scaling.
MTP/speculative decoding remains disabled because measured acceptance did not repay its additional expert I/O.
Performance depends on storage state, memory pressure, context length, routing locality, and thermals.

License and attribution

GLM-5.2 is released by Z.ai under the MIT license. See the upstream model card for architecture, training, safety, and attribution details. The historical runtime work credits antirez/ds4 and andreaborio/ds4.

Downloads last month: 98

GGUF

Model size

260B params

Architecture

glm-dsa

Hardware compatibility

2-bit

Model tree for andreaborio/GLM-5.2-DS4-GGUF

Base model

zai-org/GLM-5.2

Quantized

(113)

this model