---
base_model: THUDM/chatglm3-6b
language:
- zh
- en
tags:
- glm
- chatglm
- thudm
- llama-cpp
- gguf-my-repo
---

# hellork/chatglm3-6b-IQ4_NL-GGUF
This model was converted to GGUF format from [`THUDM/chatglm3-6b`](https://huggingface.co/THUDM/chatglm3-6b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/THUDM/chatglm3-6b) for more details on the model.

## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)

```bash
brew install llama.cpp

```
Invoke the llama.cpp server or the CLI.

### CLI:
```bash
llama-cli --hf-repo hellork/chatglm3-6b-IQ4_NL-GGUF --hf-file chatglm3-6b-iq4_nl-imat.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo hellork/chatglm3-6b-IQ4_NL-GGUF --hf-file chatglm3-6b-iq4_nl-imat.gguf -c 2048
```

### The Ship's Computer:

[whisper_dictation](https://github.com/themanyone/whisper_dictation)

Interact with this model by speaking to it. Lean, fast, & private, networked speech to text, AI images, multi-modal voice chat, control apps, webcam, and sound with less than 4GiB of VRAM.

```bash
git clone -b main --single-branch https://github.com/themanyone/whisper_dictation.git
pip install -r whisper_dictation/requirements.txt

git clone https://github.com/ggerganov/whisper.cpp
cd whisper.cpp
GGML_CUDA=1 make -j # assuming CUDA is available. see docs
ln -s server ~/.local/bin/whisper_cpp_server # (just put it somewhere in $PATH)

whisper_cpp_server -l en -m models/ggml-tiny.en.bin --port 7777
cd whisper_dictation
./whisper_cpp_client.py
```
See [the docs](https://github.com/themanyone/whisper_dictation) for tips on integrating with llama.cpp server, enabling the computer to talk back, draw AI images, carry out voice commands, and other features.

### Install Llama.cpp via git:

Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```

Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```

Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo hellork/chatglm3-6b-IQ4_NL-GGUF --hf-file chatglm3-6b-iq4_nl-imat.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo hellork/chatglm3-6b-IQ4_NL-GGUF --hf-file chatglm3-6b-iq4_nl-imat.gguf -c 2048
```