Instructions to use ubergarm/GLM-4.7-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 ubergarm/GLM-4.7-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 ubergarm/GLM-4.7-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf ubergarm/GLM-4.7-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ubergarm/GLM-4.7-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf ubergarm/GLM-4.7-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 ubergarm/GLM-4.7-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf ubergarm/GLM-4.7-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 ubergarm/GLM-4.7-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ubergarm/GLM-4.7-GGUF:Q2_K

Use Docker

docker model run hf.co/ubergarm/GLM-4.7-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use ubergarm/GLM-4.7-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ubergarm/GLM-4.7-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": "ubergarm/GLM-4.7-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ubergarm/GLM-4.7-GGUF:Q2_K

Ollama
How to use ubergarm/GLM-4.7-GGUF with Ollama:
```
ollama run hf.co/ubergarm/GLM-4.7-GGUF:Q2_K
```

Unsloth Studio

How to use ubergarm/GLM-4.7-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 ubergarm/GLM-4.7-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 ubergarm/GLM-4.7-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ubergarm/GLM-4.7-GGUF to start chatting

How to use ubergarm/GLM-4.7-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ubergarm/GLM-4.7-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": "ubergarm/GLM-4.7-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use ubergarm/GLM-4.7-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ubergarm/GLM-4.7-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 "ubergarm/GLM-4.7-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 ubergarm/GLM-4.7-GGUF with Docker Model Runner:
```
docker model run hf.co/ubergarm/GLM-4.7-GGUF:Q2_K
```

Lemonade

How to use ubergarm/GLM-4.7-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ubergarm/GLM-4.7-GGUF:Q2_K

Run and chat with the model

lemonade run user.GLM-4.7-GGUF-Q2_K

List all available models

lemonade list

Hermes Agent

How to use ubergarm/GLM-4.7-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 ubergarm/GLM-4.7-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 ubergarm/GLM-4.7-GGUF:Q2_K

Run Hermes

hermes

Atomic Chat

ubergarm commited on Dec 24, 2025

Commit

75dda6d

1 Parent(s): 4c458bf

uploading IQ5_K

Browse files

Files changed (1) hide show

README.md +63 -3

README.md CHANGED Viewed

@@ -22,8 +22,9 @@ Currently cooking this now!
 - [x] calculate imatrix and upload to HF first so others can use as desired
 - [x] cook Q8_0 and test perplexity of BF16 and Q8_0 for baseline data
 - [x] adjust MTP nextn tensors to full q8_0 (won't effect RAM+VRAM usage otherwise)
-- [ ] cook IQ5_K with full q8_0 attn/shexp/first 3 dense layers and test
-- [ ] upload IQ5_K if all looking good
 - [ ] continue with smaller quants
 - [ ] check if any folks open discussions with desired RAM/VRAM breakpoints
@@ -52,7 +53,8 @@ These first two are just test quants for baseline perplexity comparison:
 * `Q8_0` 354.794 GiB (8.505 BPW)
   - Final estimate: PPL over 565 chunks for n_ctx=512 = 3.9320 +/- 0.02428
-## IQ5_K TODO
 <details>
@@ -111,6 +113,64 @@ numactl -N ${SOCKET} -m ${SOCKET} \
 </details>
 ## Quick Start
 ```bash
 # Clone and checkout

 - [x] calculate imatrix and upload to HF first so others can use as desired
 - [x] cook Q8_0 and test perplexity of BF16 and Q8_0 for baseline data
 - [x] adjust MTP nextn tensors to full q8_0 (won't effect RAM+VRAM usage otherwise)
+- [x] cook IQ5_K with full q8_0 attn/shexp/first 3 dense layers and test
+- [x] upload IQ5_K if all looking good
+- [ ] upload smol-IQ4_KSS if all looking good
 - [ ] continue with smaller quants
 - [ ] check if any folks open discussions with desired RAM/VRAM breakpoints
 * `Q8_0` 354.794 GiB (8.505 BPW)
   - Final estimate: PPL over 565 chunks for n_ctx=512 = 3.9320 +/- 0.02428
+## IQ5_K 250.635 GiB (6.008 BPW)
+Final estimate: PPL over 565 chunks for n_ctx=512 = 3.9445 +/- 0.02439
 <details>
 </details>
+## smol-IQ4_KSS TODO
+Final estimate: PPL over 565 chunks for n_ctx=512 = TODO
+<details>
+<summary>👈 Secret Recipe</summary>
+```bash
+#!/usr/bin/env bash
+custom="
+# 93 Repeating Layers [0-92]
+# Attention
+blk\..*\.attn_q.*=q8_0
+blk\..*\.attn_k.*=q8_0
+blk\..*\.attn_v.*=q8_0
+blk\..*\.attn_output.*=q8_0
+# First 3 Dense Layers [0-2]
+blk\..*\.ffn_down\.weight=q8_0
+blk\..*\.ffn_(gate|up)\.weight=q8_0
+# Shared Expert Layers [3-92]
+blk\..*\.ffn_down_shexp\.weight=q8_0
+blk\..*\.ffn_(gate|up)_shexp\.weight=q8_0
+# Routed Experts Layers [3-92]
+blk\..*\.ffn_down_exps\.weight=iq4_kss
+blk\..*\.ffn_(gate|up)_exps\.weight=iq4_kss
+# NextN MTP Layer [92]
+blk\..*\.nextn\.embed_tokens\.weight=q8_0
+blk\..*\.nextn\.shared_head_head\.weight=q8_0
+blk\..*\.nextn\.eh_proj\.weight=q8_0
+# Non-Repeating Layers
+token_embd\.weight=iq4_k
+output\.weight=iq6_k
+"
+custom=$(
+  echo "$custom" | grep -v '^#' | \
+  sed -Ez 's:\n+:,:g;s:,$::;s:^,::'
+)
+numactl -N ${SOCKET} -m ${SOCKET} \
+./build/bin/llama-quantize \
+    --custom-q "$custom" \
+    --imatrix /mnt/data/models/ubergarm/GLM-4.7-GGUF/imatrix-GLM-4.7-BF16.dat \
+    /mnt/data/models/ubergarm/GLM-4.7-GGUF/GLM-160x21B-4.7-BF16-00001-of-00015.gguf \
+    /mnt/data/models/ubergarm/GLM-4.7-GGUF/GLM-4.7-smol-IQ4_KSS.gguf \
+    IQ4_KSS \
+    128
+```
+</details>
 ## Quick Start
 ```bash
 # Clone and checkout