Quant Request: nivvis/Step-3.5-Flash-REAP-128B-A11B-GGUF (Target 48GB)
Hi mradermacher,
Could you please provide quants for this model?
Model URL: https://huggingface.co/nivvis/Step-3.5-Flash-REAP-128B-A11B-GGUF
Specifically looking for versions around 47-48GB (like IQ3_S or IQ3_M) to fit in 64GB RAM machines with some KV cache overhead.
Thank you for your amazing work!
you provided wrong url. I assume you want me to quant that ? https://huggingface.co/lkevincc0/Step-3.5-Flash-REAP-128B-A11B
Yes, that's exactly the one! Sorry for the confusion, I provided the GGUF link by mistake.
Please go ahead and quantize lkevincc0/Step-3.5-Flash-REAP-128B-A11B. Looking forward to the IQ3_S/IQ3_M versions! Thank you!
It's queued!
You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#Step-3.5-Flash-REAP-128B-A11B-GGUF for quants to appear.