Instructions to use pratikgx/Clairic-Flash-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use pratikgx/Clairic-Flash-MLX with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("pratikgx/Clairic-Flash-MLX") config = load_config("pratikgx/Clairic-Flash-MLX") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Link the write-up on GitHub
Browse files
README.md
CHANGED
|
@@ -169,3 +169,9 @@ Also not claimed:
|
|
| 169 |
- A numerical check of the vision tower against the real Clairic vision weights.
|
| 170 |
- A bench of the 27.8B Clairic model.
|
| 171 |
- Cloudflare's hosted or synthetic-receipt evals.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 169 |
- A numerical check of the vision tower against the real Clairic vision weights.
|
| 170 |
- A bench of the 27.8B Clairic model.
|
| 171 |
- Cloudflare's hosted or synthetic-receipt evals.
|
| 172 |
+
|
| 173 |
+
<!-- github-field-notes:start -->
|
| 174 |
+
## Write-up on GitHub
|
| 175 |
+
|
| 176 |
+
How I ran this, what broke, and the scripts: [Cloudflare Clairic-flash (MLX)](https://github.com/pratikgx/local-ai-field-notes/blob/main/notes/2026-11-18-cloudflare-clairic-flash-mlx.md). It's part of [Local AI field notes](https://github.com/pratikgx/local-ai-field-notes), where I log every model I run on my Mac mini.
|
| 177 |
+
<!-- github-field-notes:end -->
|