Instructions to use pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF",
	filename="GLM-5.2-REAP50-Q2_K-00001-of-00004.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 pipenetwork/GLM-5.2-REAP50-Q2_K-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 pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf pipenetwork/GLM-5.2-REAP50-Q2_K-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 pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf pipenetwork/GLM-5.2-REAP50-Q2_K-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 pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF:Q2_K

Use Docker

docker model run hf.co/pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pipenetwork/GLM-5.2-REAP50-Q2_K-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": "pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF:Q2_K

Ollama
How to use pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF with Ollama:
```
ollama run hf.co/pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF:Q2_K
```

Unsloth Studio

How to use pipenetwork/GLM-5.2-REAP50-Q2_K-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 pipenetwork/GLM-5.2-REAP50-Q2_K-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 pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF to start chatting

How to use pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pipenetwork/GLM-5.2-REAP50-Q2_K-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": "pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use pipenetwork/GLM-5.2-REAP50-Q2_K-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 pipenetwork/GLM-5.2-REAP50-Q2_K-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 pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF:Q2_K

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf pipenetwork/GLM-5.2-REAP50-Q2_K-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 "pipenetwork/GLM-5.2-REAP50-Q2_K-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 pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF with Docker Model Runner:
```
docker model run hf.co/pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF:Q2_K
```

Lemonade

How to use pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pipenetwork/GLM-5.2-REAP50-Q2_K-GGUF:Q2_K

Run and chat with the model

lemonade run user.GLM-5.2-REAP50-Q2_K-GGUF-Q2_K

List all available models

lemonade list

pipenetwork commited on Jun 19

Commit

ea3c0f0

verified ·

1 Parent(s): 5cea7ac

Add files using upload-large-folder tool

Browse files

Files changed (7) hide show

.gitattributes +4 -0
GLM-5.2-REAP50-Q2_K-00001-of-00004.gguf +3 -0
GLM-5.2-REAP50-Q2_K-00002-of-00004.gguf +3 -0
GLM-5.2-REAP50-Q2_K-00003-of-00004.gguf +3 -0
GLM-5.2-REAP50-Q2_K-00004-of-00004.gguf +3 -0
README.md +32 -0
llama.cpp-glm-dsa-indexer-optional.patch +21 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+GLM-5.2-REAP50-Q2_K-00002-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+GLM-5.2-REAP50-Q2_K-00004-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+GLM-5.2-REAP50-Q2_K-00001-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+GLM-5.2-REAP50-Q2_K-00003-of-00004.gguf filter=lfs diff=lfs merge=lfs -text

GLM-5.2-REAP50-Q2_K-00001-of-00004.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0033c3dd3524e847b523adf5b0a0d55d8dc6dbb151e160affad941731e524bc7
+size 44999739520

GLM-5.2-REAP50-Q2_K-00002-of-00004.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:be72c34ca6f9b04646b47a0cf081d18f3387d4a8f87553b0b57e685ede66ebc0
+size 44581813248

GLM-5.2-REAP50-Q2_K-00003-of-00004.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0c1ad8c6df976317a96f3a57b1a020ef27e153008e65711cfa20a130a2083939
+size 44677711424

GLM-5.2-REAP50-Q2_K-00004-of-00004.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:313a335f1fad23a8ee6944060c0e44e01e6ea7acec7b6e316a16ab9edcd54469
+size 4731875104

README.md ADDED Viewed

	@@ -0,0 +1,32 @@

+---
+license: mit
+base_model: zai-org/GLM-5.2
+base_model_relation: quantized
+pipeline_tag: text-generation
+library_name: gguf
+tags: [gguf, llama.cpp, moe, glm, reap, pruned]
+---
+# GLM-5.2-REAP50-Q2_K-GGUF
+GGUF of GLM-5.2, **REAP expert-pruned (50%)** + **Q2_K** (~129 GB) — the **maximum-context** option for **2× 96 GB GPUs (192 GB)**, leaving ~60 GB for KV cache (≈2.5× the context room of the Q3_K build).
+## ⚠️ Quality: fragile — most-degraded variant
+This stacks REAP-50 (~+37.5% perplexity vs full GLM-5.2) **with 2-bit Q2_K**. It **works but is delicate**:
+- ✅ Coherent with sampling: *"The capital city of France … is Paris."*
+- ❌ **Collapses into repetition (`* * * *`) with greedy / temp 0 decoding.**
+**Use these sampler settings** (or it may loop):
+```
+--temp 0.6 --repeat-penalty 1.1 --top-p 0.95
+```
+If you can spare the VRAM, the **[Q3_K_M build](https://huggingface.co/pipenetwork/GLM-5.2-REAP50-Q3_K_M-GGUF)** (~169 GB) is noticeably more robust. For real quality, use the MLX REAP-25 (+2.3% PPL) or full GLM-5.2.
+## Requires a patched llama.cpp
+Stock llama.cpp can't load GLM-5.2 GGUFs yet (DSA indexer required on every layer; GLM-5.2 ships it on only some). Apply the included `llama.cpp-glm-dsa-indexer-optional.patch` (or wait for [ggml-org/llama.cpp#24770](https://github.com/ggml-org/llama.cpp/pull/24770)), rebuild, then:
+```bash
+./build/bin/llama-cli -m GLM-5.2-REAP50-Q2_K-00001-of-00004.gguf --jinja -ngl 99 \
+  --temp 0.6 --repeat-penalty 1.1 -p "..."
+```
+REAP-50 = top-128 of 256 experts/layer by saliency; runs as full MLA attention. Smoke-tested on Metal (~20 tok/s).

llama.cpp-glm-dsa-indexer-optional.patch ADDED Viewed

	@@ -0,0 +1,21 @@

+diff --git a/src/models/glm-dsa.cpp b/src/models/glm-dsa.cpp
+index 11d9131..32fe6de 100644
+--- a/src/models/glm-dsa.cpp
++++ b/src/models/glm-dsa.cpp
+@@ -101,11 +101,11 @@ void llama_model_glm_dsa::load_arch_tensors(llama_model_loader &) {
+         layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, flags);
+         // DSA indexer
+-        layer.indexer_k_norm   = create_tensor(tn(LLM_TENSOR_INDEXER_K_NORM,   "weight", i), {hparams.indexer_head_size}, flags);
+-        layer.indexer_k_norm_b = create_tensor(tn(LLM_TENSOR_INDEXER_K_NORM,   "bias",   i), {hparams.indexer_head_size}, flags);
+-        layer.indexer_proj     = create_tensor(tn(LLM_TENSOR_INDEXER_PROJ,     "weight", i), {n_embd, hparams.indexer_n_head}, flags);
+-        layer.indexer_attn_k   = create_tensor(tn(LLM_TENSOR_INDEXER_ATTN_K,   "weight", i), {n_embd, hparams.indexer_head_size}, flags);
+-        layer.indexer_attn_q_b = create_tensor(tn(LLM_TENSOR_INDEXER_ATTN_Q_B, "weight", i), {q_lora_rank, hparams.indexer_n_head * hparams.indexer_head_size}, flags);
++        layer.indexer_k_norm   = create_tensor(tn(LLM_TENSOR_INDEXER_K_NORM,   "weight", i), {hparams.indexer_head_size}, flags | TENSOR_NOT_REQUIRED);
++        layer.indexer_k_norm_b = create_tensor(tn(LLM_TENSOR_INDEXER_K_NORM,   "bias",   i), {hparams.indexer_head_size}, flags | TENSOR_NOT_REQUIRED);
++        layer.indexer_proj     = create_tensor(tn(LLM_TENSOR_INDEXER_PROJ,     "weight", i), {n_embd, hparams.indexer_n_head}, flags | TENSOR_NOT_REQUIRED);
++        layer.indexer_attn_k   = create_tensor(tn(LLM_TENSOR_INDEXER_ATTN_K,   "weight", i), {n_embd, hparams.indexer_head_size}, flags | TENSOR_NOT_REQUIRED);
++        layer.indexer_attn_q_b = create_tensor(tn(LLM_TENSOR_INDEXER_ATTN_Q_B, "weight", i), {q_lora_rank, hparams.indexer_n_head * hparams.indexer_head_size}, flags | TENSOR_NOT_REQUIRED);
+         if (i < (int) hparams.n_layer_dense_lead) {
+             layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd,   n_ff}, flags);
+             layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {  n_ff, n_embd}, flags);