Hcompany/Holo2-4B

Full fine-tune vs Qwen/Qwen3-VL-4B-Thinking. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 4/4, Norms 249/249, MLP 220/220, Attention 240/240

2 derivatives checked

• mradermacher/Holo2-4B-GGUF: Same weights, converted (fewer layers)
• mradermacher/Holo2-4B-i1-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse