EINSOF-II Granite 3.3 8B Qiskit Stiefel (GGUF Quantizations)

  • Base Model: Qiskit/granite-3.3-8b-qiskit
  • Adapter: Polydim-Einsof/einsof2-granite-8b-qiskit-stiefel-adapter
  • Quantizations: Q4_K_M (4.60 GB) and Q8_0 (8.09 GB)
  • Manifold: Stiefel S^(D-1) via polar retraction order 4
  • Framework: llama.cpp + POLYDIM PMTP
Downloads last month
83
GGUF
Model size
8B params
Architecture
granite
Hardware compatibility
Log In to add your hardware

4-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Polydim-Einsof/einsof2-granite-8b-qiskit-stiefel-gguf