Text Generation
MLX
Safetensors
deepseek_v4
deepseek
deepseek-v4
deepseek-v4-flash-0731
mixture-of-experts
mla
reasoning
tool-use
dsml
apple-silicon
quantized
jang
affine
qat
osaurus
Instructions to use OsaurusAI/DeepSeek-V4-Flash-0731-JANG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OsaurusAI/DeepSeek-V4-Flash-0731-JANG with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("OsaurusAI/DeepSeek-V4-Flash-0731-JANG") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use OsaurusAI/DeepSeek-V4-Flash-0731-JANG with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "OsaurusAI/DeepSeek-V4-Flash-0731-JANG" --prompt "Once upon a time"
Ctrl+K
- encoding
- 30.8 kB
- 1.52 kB
- 1.08 kB
- 8.56 kB
- 2.13 MB xet
- 1.42 MB
- 1.6 kB
- 1.44 kB
- 2 kB
- 801 Bytes
- 272 Bytes
- 8.2 kB
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1.01 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet
- 1 GB xet