Joseph717171/
Hermes-3-Llama-3.2-3B-OQ8_0-F32.EF32.IQ4_K-Q8_0-GGUF

Name: Hermes-3-Llama-3.2-3B-OQ8_0-F32.EF32.IQ4_K-Q8_0-GGUF
Availability: InStock

like

0

Views

No views yet

Custom GGUF quants of Hermes-3-Llama-3.2-3B, where the Output Tensors are quantized to Q8_0 or upcast to F32, while the Embeddings are kept at F32. Enjoy! 🧠🔥🚀

Joseph717171/Hermes-3-Llama-3.2-3B-OQ8_0-F32.EF32.IQ4_K-Q8_0-GGUF

Joseph717171/
Hermes-3-Llama-3.2-3B-OQ8_0-F32.EF32.IQ4_K-Q8_0-GGUF