Post
140
Run Inkling 2 Mini, the strongest 26.4B model that runs on 16GB RAM.
Thinking Machines’ Apache 2.0 MoE model uses a looped transformer arch & scores 48.2% on DeepSWE v1.1, the best for size.
Run on Unsloth Desktop or llama.cpp.
GGUF: unsloth/Inkling-2-Mini-GGUF
Guide: https://unsloth.ai/docs/models/inkling-2-mini
Thinking Machines’ Apache 2.0 MoE model uses a looped transformer arch & scores 48.2% on DeepSWE v1.1, the best for size.
Run on Unsloth Desktop or llama.cpp.
GGUF: unsloth/Inkling-2-Mini-GGUF
Guide: https://unsloth.ai/docs/models/inkling-2-mini