mradermacher/Qwen3-16B-A3B-Base-GGUF

Full fine-tune vs Columbidae/Qwen3-16B-A3B-Base. mradermacher/Qwen3-16B-A3B-Base-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: Embeddings 1/1, Norms 0/193, MLP 47/48, Attention 192/192, lm_head 1/1

On the Hub · Downloads on Model Pulse