Text Generation
MLX
Safetensors
English
Chinese
deepseek_v4
deepseek-v4
deepseek
quantized
apple-silicon
mixture-of-experts
Mixture of Experts
mxtq
turboquant
jang
jangtq
conversational
2.3-bit
Instructions to use osmapi/DeepSeek-V4-Flash-TQ-Q2.3-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use osmapi/DeepSeek-V4-Flash-TQ-Q2.3-MLX with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("osmapi/DeepSeek-V4-Flash-TQ-Q2.3-MLX") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use osmapi/DeepSeek-V4-Flash-TQ-Q2.3-MLX with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "osmapi/DeepSeek-V4-Flash-TQ-Q2.3-MLX"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "osmapi/DeepSeek-V4-Flash-TQ-Q2.3-MLX" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "osmapi/DeepSeek-V4-Flash-TQ-Q2.3-MLX", "messages": [ {"role": "user", "content": "Hello"} ] }'
- Xet hash:
- ec6bdffeeca9b05020017e448ba5d01520c2e37f8010c78aa962269ad6cd0cc2
- Size of remote file:
- 1.08 GB
- SHA256:
- 8788378d2f059eee4c8a9c2633a9d1b9ef09a689271cf0bdc350f1440d5ab000
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.