Text Generation
MLX
Safetensors
deepseek_v4
apple-silicon
quantized
mixed-precision
axquant
axq
development
deepseek-v4
6bit
6-bit
mtp
4-bit precision
Instructions to use AutomatosX/AX-DeepSeek-V4-Flash-MLX-AXQ-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AutomatosX/AX-DeepSeek-V4-Flash-MLX-AXQ-6bit 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("AutomatosX/AX-DeepSeek-V4-Flash-MLX-AXQ-6bit") 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 AutomatosX/AX-DeepSeek-V4-Flash-MLX-AXQ-6bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "AutomatosX/AX-DeepSeek-V4-Flash-MLX-AXQ-6bit" --prompt "Once upon a time"
- Atomic Chat
Ctrl+K
- 1.57 kB
- 8.05 kB
- 13.9 kB
- 938 Bytes
- 63.4 MB xet
- 8.05 MB
- 1.68 kB
- 160 kB
- 170 Bytes
- 4.89 GB xet
- 4.2 GB xet
- 4.19 GB xet
- 4.2 GB xet
- 4.19 GB xet
- 4.2 GB xet
- 4.19 GB xet
- 4.2 GB xet
- 4.19 GB xet
- 4.2 GB xet
- 4.19 GB xet
- 4.2 GB xet
- 4.19 GB xet
- 4.2 GB xet
- 4.19 GB xet
- 4.2 GB xet
- 4.19 GB xet
- 4.2 GB xet
- 4.19 GB xet
- 4.2 GB xet
- 4.19 GB xet
- 4.2 GB xet
- 4.19 GB xet
- 4.2 GB xet
- 5.37 GB xet
- 5.33 GB xet
- 5.34 GB xet
- 3.78 GB xet
- 5.27 GB xet
- 5.26 GB xet
- 2.19 GB xet
- 5.36 GB xet
- 5.33 GB xet
- 5.36 GB xet
- 5.32 GB xet
- 5.34 GB xet
- 3.79 GB xet
- 5.28 GB xet
- 5.26 GB xet
- 2.19 GB xet
- 5.36 GB xet