AgentionAI releases Gyro Coder Large, a 32GB VRAM coding finetune of Qwen 3.8 Flash Next

·2026.10.24 01:16

Key point

The coding-specific finetune of Qwen 3.8 Flash Next matches the size of Gyro-S while using half the experts and more bits per expert.

AgentionAI has released Gyro Coder Large, a coding-specific finetune of Qwen 3.8 Flash Next.
The model is the same size as Gyro-S but utilizes half the number of experts with more bits per expert.
The model requires 32GB of VRAM to run.
Additional technical details are provided in the model card.

This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.

Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.