[DEPRECATED] Humotica 7B OOM
This model is deprecated. Use Qwen2.5-7B-Instruct-OOM instead.
The model file in this repo was converted via GGUF (Q3_K -> Q8 double quantization), which causes output degradation.
The new repo uses direct SafeTensors conversion (bf16 -> Q8, single quantization step) with verified correct output.
New Model
Use this instead: jaspervandemeent/Qwen2.5-7B-Instruct-OOM
Built by Humotica AI Lab
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support