EnlistedGhost/Magistral-Small-2509-Vision

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 64/131, MLP 192/192, Attention 256/256, other 4/4, lm_head 1/1

3 derivatives checked

• EnlistedGhost/Magistral-Small-2509-Vision-GGUF: Same weights, converted (fewer layers)
• mradermacher/Magistral-Small-2509-Vision-i1-GGUF: Quantization (fewer layers)
• mradermacher/Magistral-Small-2509-Vision-GGUF: Quantization (fewer layers)

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse