@MuleDeer84@MxMnr It looks like Unsloth GGUFs don’t work with llama.cpp master. Please download the quant from LM staff picks. They are made with llama.cpp mainline
@MuleDeer84@MxMnr It looks like Unsloth GGUFs don’t work with llama.cpp master. Please download the quant from LM staff picks. They are made with llama.cpp mainline
Inkling 2 Mini by @thinkymachines is now in LM Studio!
It's a 26B looped transformer. Requires ~18GB to run locally, Apache 2.0 licensed.
Leads among <100B models on DeepSWE v1.1 (48.2%) and Vals Index v2.2 (46.5%)
🚀🚀🚀
Inkling 2 Mini by @thinkymachines is now in LM Studio!
It's a 26B looped transformer. Requires ~18GB to run locally, Apache 2.0 licensed.
Leads among <100B models on DeepSWE v1.1 (48.2%) and Vals Index v2.2 (46.5%)
🚀🚀🚀
Some of you thought that Inkling 2 Small was too big at 594B parameters. We heard you: Inkling 2 Mini is a looped transformer with just 26B parameters, small enough to run on your laptop, powerful enough for agentic work with a score of 20.1 on AA Index.
https://t.co/9HzaUMwghb