Hcompany/Holo2-235B-A22B

Full fine-tune vs Qwen/Qwen3-VL-235B-A22B-Thinking. Fine-tune: 100% of the weights changed, across 94 of 94 layers.

Tensors changed: Embeddings 4/4, MLP 400/406, Norms 446/493, Attention 484/484, lm_head 1/1

2 derivatives checked

• mradermacher/Holo2-235B-A22B-i1-GGUF: Quantization
• mradermacher/Holo2-235B-A22B-GGUF: Quantization

On the Hub · Downloads on Model Pulse