Entity-27th/Magnum-Opus-35B-A3B

Uploaded finetuned model

• Developed by: Entity-27th
• License: apache-2.0
• Finetuned from model : unsloth/Qwen3.5-35B-A3B
• Hardware used: AMD Instinct MI300X x 1

This qwen3_5_moe model was trained 2x faster with Unsloth and Huggingface's TRL library.

This is a fine-tuned version of Qwen3.5-35B-A3B trained in Opus-4.6-Reasoning-3000x-filtered dataset with LoRA. It was trained on a single MI300X card.