llama3-8b-spaetzle-v33-mlx-4bit

cstr/llama3-8b-spaetzle-v33-mlx-4bit

The Model cstr/llama3-8b-spaetzle-v33-mlx-4bit was converted to MLX format from cstr/llama3-8b-spaetzle-v33 using mlx-lm version 0.14.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("cstr/llama3-8b-spaetzle-v33-mlx-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)

Provenance and EU AI Act Art. 53 note

• Base model: cstr/llama3-8b-spaetzle-v33 — a mergekit merge published by the same maintainer as this repository. It is not a third-party upstream: the maintainer authored that model.
• What was done here: format conversion and/or quantisation of that base model only (MLX, INT4 precision). No further training, fine-tuning or merging was applied at this step.
• Licence: llama3, inherited through the base model from the models it was built from.
• Training data: none was used, added or selected at this conversion step. The base model's card lists the models it was built from; their training content is documented — where it is documented at all — by their respective providers.
• Provider status: under Regulation (EU) 2024/1689 this repository makes no provider claim for the conversion step. Any provider obligations attaching to the model itself — including Art. 53(1)(c) copyright policy and Art. 53(1)(d) training-content summary — attach at cstr/llama3-8b-spaetzle-v33, not here.