unsloth/Inkling-Small-GGUF
Not comparable yet vs thinkingmachines/Inkling-Small. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (1 of 1048/960 match), usually an architecture llama.cpp's name map doesn't cover yet.
3 derivatives checked
- lyssquant/Inkling-Small-UD-Q4_K_XL-layers: Quantization (fewer layers)
- zurichquants/Inkling-Small-UD-Q4_K_XL-layers: Quantization (fewer layers)
- shaffhausen/Inkling-Small-UD-Q4_K_XL-layers: Quantization (fewer layers)