nvidia/NFT-32B

Full fine-tune vs Qwen/Qwen2.5-32B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 1/1, Norms 127/129, MLP 192/192, Attention 448/448, lm_head 1/1

3 derivatives checked

• gabriellarson/NFT-32B-GGUF: Quantization
• mradermacher/NFT-32B-i1-GGUF: Quantization
• mradermacher/NFT-32B-GGUF: Quantization

On the Hub · Downloads on Model Pulse