Thank you Daniel!
Would it be possible to you to add your quantized version of https://huggingface.co/models?other=base_model:quantized:ServiceNow-AI/Apriel-1.6-15b-Thinker
namely the Q8_K_XL?
Your Apriel-1.5-15b_Q8_K_XL is very good and I am not getting the good results with the Apriel-1.5-15b_Q8_0 version available in huggingface.
charles muntz
chmuntz
AI & ML interests
None yet
Recent Activity
replied to
danielhanchen's
post
16 days ago
NVIDIA releases Nemotron 3 Nano, a new 30B hybrid reasoning model! š„
Has 1M context window & best in class performance for SWE-Bench, reasoning & chat. Run the MoE model locally with 24GB RAM.
GGUF: https://huggingface.co/unsloth/Nemotron-3-Nano-30B-A3B-GGUF
š Step-by-step Guide: https://docs.unsloth.ai/models/nemotron-3
liked
a model
about 1 month ago
nvidia/Nemotron-Elastic-12B
Organizations
None yet
replied to
danielhanchen's
post
16 days ago
liked
a
model
about 1 month ago
