Text Generation
MLX
Safetensors
deepseek_v41
gbx-lm
apple-silicon
mixture-of-experts
4-bit precision
expert-paging
fp8
Instructions to use GreenBitAI/DeepSeek-V4.1-Flash-4bit-paged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use GreenBitAI/DeepSeek-V4.1-Flash-4bit-paged 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("GreenBitAI/DeepSeek-V4.1-Flash-4bit-paged") 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 GreenBitAI/DeepSeek-V4.1-Flash-4bit-paged with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "GreenBitAI/DeepSeek-V4.1-Flash-4bit-paged" --prompt "Once upon a time"
- Atomic Chat
Ctrl+K
- engram-layer-1
- engram-layer-14
- mtp
- 1.56 kB
- 7.58 kB
- 54.1 kB
- 875 kB
- 306 GB xet
- 3.29 kB
- 2.14 kB
- 2.47 kB
- 2.55 kB
- 2.14 kB
- 2.14 kB
- 2.14 kB
- 2.14 kB
- 2.14 kB
- 2.55 kB
- 2.14 kB
- 2.19 kB
- 2.19 kB
- 2.19 kB
- 2.19 kB
- 2.96 kB
- 2.19 kB
- 2.19 kB
- 2.19 kB
- 2.19 kB
- 2.19 kB
- 2.57 kB
- 2.19 kB
- 2.19 kB
- 2.19 kB
- 2.41 kB
- 2.19 kB
- 2.19 kB
- 2.19 kB
- 2.41 kB
- 2.19 kB
- 2.19 kB
- 2.19 kB
- 2.41 kB
- 2.19 kB
- 2.19 kB
- 2.19 kB
- 2.41 kB
- 2.19 kB
- 2.19 kB
- 2.19 kB
- 238 Bytes