Text Generation
MLX
Safetensors
deepseek_v4
apple-silicon
quantized
mixed-precision
axquant
axq
development
deepseek-v4
3bit
3-bit
mtp
Instructions to use AutomatosX/AX-DeepSeek-V4-Flash-MLX-AXQ-3bit 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-3bit 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-3bit") 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-3bit 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-3bit" --prompt "Once upon a time"
- Xet hash:
- 7c18d7cec7a0dbcbc91896819e8f7c52ab6f82836551f6a75ada2405f337b8ef
- Size of remote file:
- 61.2 MB
- SHA256:
- 8b348d337fd61597c7c067fffb5f7d8059b6bbc04a0b6721b5309f341ce3d6f3
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.