Instructions to use b2z/Smaug-Flash-oQ8-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use b2z/Smaug-Flash-oQ8-mtp 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("b2z/Smaug-Flash-oQ8-mtp") 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 b2z/Smaug-Flash-oQ8-mtp with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "b2z/Smaug-Flash-oQ8-mtp" --prompt "Once upon a time"
- Atomic Chat
Ctrl+K
- 1.52 kB
- 9.65 kB
- 121 kB
- 170 Bytes
- 5 GB xet
- 5.67 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 5.7 GB xet
- 1.14 GB xet
- 184 kB
- 6.37 MB
- 801 Bytes