Text Generation
Safetensors
English
minimax
gptqmodel
modelcloud
chat
glm4.6
glm
instruct
int4
gptq
4bit
w4a16
conversational
custom_code
4-bit precision
Instructions to use ModelCloud/MiniMax-M2-GPTQMODEL-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- vLLM
How to use ModelCloud/MiniMax-M2-GPTQMODEL-W4A16 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ModelCloud/MiniMax-M2-GPTQMODEL-W4A16" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ModelCloud/MiniMax-M2-GPTQMODEL-W4A16", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ModelCloud/MiniMax-M2-GPTQMODEL-W4A16
- SGLang
How to use ModelCloud/MiniMax-M2-GPTQMODEL-W4A16 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "ModelCloud/MiniMax-M2-GPTQMODEL-W4A16" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ModelCloud/MiniMax-M2-GPTQMODEL-W4A16", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "ModelCloud/MiniMax-M2-GPTQMODEL-W4A16" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ModelCloud/MiniMax-M2-GPTQMODEL-W4A16", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use ModelCloud/MiniMax-M2-GPTQMODEL-W4A16 with Docker Model Runner:
docker model run hf.co/ModelCloud/MiniMax-M2-GPTQMODEL-W4A16
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,7 +7,9 @@ license_link: LICENSE
|
|
| 7 |
This 4bit W4A16 model has been quantized by <a href='https://x.com/qubitium'>@Qubitum</a> at ModelCloud using
|
| 8 |
[GPT-QModel](https://github.com/ModelCloud/GPTQModel).
|
| 9 |
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
|
|
|
|
|
|
|
|
| 7 |
This 4bit W4A16 model has been quantized by <a href='https://x.com/qubitium'>@Qubitum</a> at ModelCloud using
|
| 8 |
[GPT-QModel](https://github.com/ModelCloud/GPTQModel).
|
| 9 |
|
| 10 |
+
```
|
| 11 |
+
SPDX-License-Identifier: NonCommercial-ModelCloud
|
| 12 |
+
Copyright (c) 2024–2025 ModelCloud.ai
|
| 13 |
+
Released for non-profit use only.
|
| 14 |
+
Commercial use requires permission from [@qubitium](https://x.com/qubitium).
|
| 15 |
+
```
|