OctoMed/OctoMed-8B

Full fine-tune vs Qwen/Qwen3-VL-8B-Instruct. Fine-tune: 94% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 1/4, Norms 145/261, MLP 112/232, Attention 144/252, lm_head 1/1

2 derivatives checked

• mradermacher/OctoMed-8B-i1-GGUF: Quantization (fewer layers)
• mradermacher/OctoMed-8B-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse