Instructions to use concedo/GLM-ASR-Nano-2512-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use concedo/GLM-ASR-Nano-2512-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="concedo/GLM-ASR-Nano-2512-GGUF",
	filename="GLM-ASR-Nano-1.6B-2512-BF16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use concedo/GLM-ASR-Nano-2512-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf concedo/GLM-ASR-Nano-2512-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf concedo/GLM-ASR-Nano-2512-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf concedo/GLM-ASR-Nano-2512-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf concedo/GLM-ASR-Nano-2512-GGUF:BF16

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 concedo/GLM-ASR-Nano-2512-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf concedo/GLM-ASR-Nano-2512-GGUF:BF16

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 concedo/GLM-ASR-Nano-2512-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf concedo/GLM-ASR-Nano-2512-GGUF:BF16

Use Docker

docker model run hf.co/concedo/GLM-ASR-Nano-2512-GGUF:BF16

LM Studio
Jan
Ollama
How to use concedo/GLM-ASR-Nano-2512-GGUF with Ollama:
```
ollama run hf.co/concedo/GLM-ASR-Nano-2512-GGUF:BF16
```

Unsloth Studio new

How to use concedo/GLM-ASR-Nano-2512-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 concedo/GLM-ASR-Nano-2512-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 concedo/GLM-ASR-Nano-2512-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for concedo/GLM-ASR-Nano-2512-GGUF to start chatting

Docker Model Runner
How to use concedo/GLM-ASR-Nano-2512-GGUF with Docker Model Runner:
```
docker model run hf.co/concedo/GLM-ASR-Nano-2512-GGUF:BF16
```

Lemonade

How to use concedo/GLM-ASR-Nano-2512-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull concedo/GLM-ASR-Nano-2512-GGUF:BF16

Run and chat with the model

lemonade run user.GLM-ASR-Nano-2512-GGUF-BF16

List all available models

lemonade list

These GGUF quants were made from https://huggingface.co/zai-org/GLM-ASR-Nano-2512 and designed for use in KoboldCpp 1.104 and above.

Contains 3 GGUF quants of GLM-ASR-Nano-2512, as well as the associated mmproj file.

To use:

Download the main model (GLM-ASR-Nano-1.6B-2512-Q4_K.gguf) and the mmproj (mmproj-GLM-ASR-Nano-2512-Q8_0.gguf)
Launch KoboldCpp and go to Loaded Files tab
Select the main model as "Text Model" and the mmproj as "mmproj"

Downloads last month: 282

GGUF

Model size

2B params

Architecture

llama

Hardware compatibility

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for concedo/GLM-ASR-Nano-2512-GGUF

Base model

zai-org/GLM-ASR-Nano-2512

Quantized

(3)

this model