Qwen3.8-2B-Distill-heretic

Model source

Published by htb-ac-1424625 on Hugging Face. This index organizes public repository metadata for discovery and comparison. Refer to the publisher and independent testing for actual model behavior.

Declared base model

Qwen/Qwen3.5-2B ↗

Hardware and context

Estimated at 2.1 GB VRAM for 2B parameters with 4-bit weights, including 15% weight overhead and 1 GB of baseline headroom. KV cache, context length, multimodal components and concurrency increase actual memory usage.The parameter count was parsed from the model name and has not been independently verified.

Context length: Not stated in public metadata. Please consult the model card.