Joseph717171/
Granite-3.1-8B-instruct-OQ8_0-F32.EF32.IQ4_K-Q8_0-GGUF

Name: Granite-3.1-8B-instruct-OQ8_0-F32.EF32.IQ4_K-Q8_0-GGUF
Availability: InStock

like

0

Views

No views yet

Custom GGUF quants of ibm-granite/granite-3.1-8b-instruct, where the Output Tensors are quantized to Q8_0 or upcast to F32, while the Embeddings are kept at F32. Enjoy! 🧠🔥🚀

Joseph717171/Granite-3.1-8B-instruct-OQ8_0-F32.EF32.IQ4_K-Q8_0-GGUF

Joseph717171/
Granite-3.1-8B-instruct-OQ8_0-F32.EF32.IQ4_K-Q8_0-GGUF