Qiskit/mistral-small-3.2-24b-qiskit

Full fine-tune vs mistralai/Mistral-Small-3.2-24B-Instruct-2506. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 40/131, MLP 192/192, Attention 256/256, other 4/4, lm_head 1/1

1 derivatives checked

• Qiskit/mistral-small-3.2-24b-qiskit-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse