qkv-core/qkv-core
qkv-core/qkv-core: "Adaptive Hybrid Quantization Framework for deploying 7B+ LLMs on low-VRAM devices (e.g., GTX 1050). Features surgical block alignment and Numba-accelerated inference. License: mit. Hugging Bay hosted release. Scan: pending.
- License
- mit
- Scan status
- pending
- Hosting status
- external
- Upstream
- QKV-Core/QKV-Core
Open interactive artifact page