Instructions to use gannima/AutoGLM-Phone-9B-Multilingual-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gannima/AutoGLM-Phone-9B-Multilingual-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="gannima/AutoGLM-Phone-9B-Multilingual-GGUF",
	filename="AutoGLM-Phone-9B-Multilingual-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use gannima/AutoGLM-Phone-9B-Multilingual-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf gannima/AutoGLM-Phone-9B-Multilingual-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf gannima/AutoGLM-Phone-9B-Multilingual-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf gannima/AutoGLM-Phone-9B-Multilingual-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf gannima/AutoGLM-Phone-9B-Multilingual-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 gannima/AutoGLM-Phone-9B-Multilingual-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf gannima/AutoGLM-Phone-9B-Multilingual-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 gannima/AutoGLM-Phone-9B-Multilingual-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf gannima/AutoGLM-Phone-9B-Multilingual-GGUF:Q4_K_M

Use Docker

docker model run hf.co/gannima/AutoGLM-Phone-9B-Multilingual-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use gannima/AutoGLM-Phone-9B-Multilingual-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gannima/AutoGLM-Phone-9B-Multilingual-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": "gannima/AutoGLM-Phone-9B-Multilingual-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gannima/AutoGLM-Phone-9B-Multilingual-GGUF:Q4_K_M

Ollama
How to use gannima/AutoGLM-Phone-9B-Multilingual-GGUF with Ollama:
```
ollama run hf.co/gannima/AutoGLM-Phone-9B-Multilingual-GGUF:Q4_K_M
```

Unsloth Studio new

How to use gannima/AutoGLM-Phone-9B-Multilingual-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 gannima/AutoGLM-Phone-9B-Multilingual-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 gannima/AutoGLM-Phone-9B-Multilingual-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for gannima/AutoGLM-Phone-9B-Multilingual-GGUF to start chatting

Docker Model Runner
How to use gannima/AutoGLM-Phone-9B-Multilingual-GGUF with Docker Model Runner:
```
docker model run hf.co/gannima/AutoGLM-Phone-9B-Multilingual-GGUF:Q4_K_M
```

Lemonade

How to use gannima/AutoGLM-Phone-9B-Multilingual-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull gannima/AutoGLM-Phone-9B-Multilingual-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.AutoGLM-Phone-9B-Multilingual-GGUF-Q4_K_M

List all available models

lemonade list

gannima commited on Dec 30, 2025

Commit

d616423

verified ·

1 Parent(s): 1515a11

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +21 -17

README.md CHANGED Viewed

@@ -25,10 +25,10 @@ This is a **GGUF** quantized version of [zai-org/AutoGLM-Phone-9B-Multilingual](
 | File | Quantization | Size | VRAM | Description |
 |------|-------------|------|------|-------------|
-| `AutoGLM-Phone-9B-Multilingual-q4_k_m.gguf` | Q4_K_M | 5.7G | 16GB | Performance balanced |
-| `AutoGLM-Phone-9B-Multilingual-q5_k_m.gguf` | Q5_K_M | 6.6G | 20GB | High quality |
-| `AutoGLM-Phone-9B-Multilingual-q6_k.gguf` | Q6_K | 7.7G | 24GB | Excellent quality |
-| `AutoGLM-Phone-9B-Multilingual-q8_0.gguf` | Q8_0 | 9.4G | 24GB+ | Best quality |
 | `mmproj-AutoGLM-Phone-9B-Multilingual-F16.gguf` | F16 | 1.7G | - | Vision Encoder (required) |
 **Total storage**: ~31GB (all quantizations + vision encoder)
@@ -78,14 +78,16 @@ python main.py \
 ## 💻 Hardware Requirements
-### Quick Reference
-| Quantization | Model Size | Vision Encoder | Total | Min VRAM | Recommended GPU | Quality |
-|--------------|------------|----------------|-------|----------|-----------------|---------|
-| Q4_K_M | 5.7G | 1.7G | ~7.4G | 16GB | RTX 4080 / 4070 Ti | Good |
-| Q5_K_M | 6.6G | 1.7G | ~8.3G | 20GB | RTX 4090 / 3090 | Very Good |
-| Q6_K | 7.7G | 1.7G | ~9.4G | 24GB | RTX 4090 | Excellent |
-| Q8_0 | 9.4G | 1.7G | ~11.1G | 24GB+ | RTX 4090 / A6000 | Best |
 ### System Requirements
@@ -101,6 +103,7 @@ python main.py \
 - **KV Cache**: Quantized to Q8_0 to reduce memory usage
 - **Batch Size**: Optimized for RTX 4090 (adjust based on your GPU)
 - **Context**: Supports up to 32K tokens with M-RoPE
 ## 🎯 Recommended Usage
@@ -112,15 +115,15 @@ Use **Q5_K_M** or **Q6_K** for the best balance between quality and performance:
 ### For Maximum Quality
 Use **Q8_0** when:
-- VRAM is not a constraint
-- You need the highest possible accuracy
-- Running complex multi-step tasks
-### For Constrained Hardware
 Use **Q4_K_M** when:
-- Limited VRAM (16GB)
 - Need faster inference
-- Running on consumer GPUs
 ## 📄 License
@@ -137,3 +140,4 @@ https://huggingface.co/zai-org/AutoGLM-Phone-9B-Multilingual
 **Conversion Date**: 2025-12-29
 **llama.cpp Version**: latest (with GLM4V support)

 | File | Quantization | Size | VRAM | Description |
 |------|-------------|------|------|-------------|
+| `AutoGLM-Phone-9B-Multilingual-q4_k_m.gguf` | Q4_K_M | 5.7G | ~10GB | Performance balanced |
+| `AutoGLM-Phone-9B-Multilingual-q5_k_m.gguf` | Q5_K_M | 6.6G | ~11GB | High quality |
+| `AutoGLM-Phone-9B-Multilingual-q6_k.gguf` | Q6_K | 7.7G | ~12GB | Excellent quality |
+| `AutoGLM-Phone-9B-Multilingual-q8_0.gguf` | Q8_0 | 9.4G | ~14GB | Best quality |
 | `mmproj-AutoGLM-Phone-9B-Multilingual-F16.gguf` | F16 | 1.7G | - | Vision Encoder (required) |
 **Total storage**: ~31GB (all quantizations + vision encoder)
 ## 💻 Hardware Requirements
+### Quick Reference (Tested on RTX 4090)
+| Quantization | Model Size | Vision Encoder | Total | Actual VRAM* | Quality |
+|--------------|------------|----------------|-------|--------------|---------|
+| Q4_K_M | 5.7G | 1.7G | ~7.4G | ~10GB | Good |
+| Q5_K_M | 6.6G | 1.7G | ~8.3G | ~11GB | Very Good |
+| Q6_K | 7.7G | 1.7G | ~9.4G | ~12GB | Excellent |
+| Q8_0 | 9.4G | 1.7G | ~11.1G | ~14GB | Best |
+\*VRAM usage measured with `--flash-attn on` and all layers on GPU (`-ngl 99`)
 ### System Requirements
 - **KV Cache**: Quantized to Q8_0 to reduce memory usage
 - **Batch Size**: Optimized for RTX 4090 (adjust based on your GPU)
 - **Context**: Supports up to 32K tokens with M-RoPE
+- **All layers on GPU**: Set `-ngl 99` to offload all transformer layers to GPU
 ## 🎯 Recommended Usage
 ### For Maximum Quality
 Use **Q8_0** when:
+- You want the highest possible accuracy
+- Running on RTX 4090 or better
+- Complex multi-step GUI automation tasks
+### For Consumer GPUs
 Use **Q4_K_M** when:
+- Limited VRAM (12GB cards like RTX 4070)
 - Need faster inference
+- Running on gaming GPUs
 ## 📄 License
 **Conversion Date**: 2025-12-29
 **llama.cpp Version**: latest (with GLM4V support)
+**Tested Hardware**: RTX 4090 24GB