Inkling-2-Mini

See Inkling-2-Mini in action: demonstration videos

Tested with Inferencer v2.5.4

M3 Ultra
  • 500 Tokens: ~31 tokens/s ~16.5 GiB
M3 Ultra with MTP (Enable in Inference controls > Engine)
  • 500 Tokens (Coding): ~37 tokens/s ~17.1 GiB

This build repacks the existing quantized weights and quantizes the remaining layers to 9 bits for near lossless quality.

Screenshot

Quantized with a modified version of MLX
For more details see our demonstration videos or visit Inkling-2-Mini.

Disclaimer

We are not the creator, originator, or owner of any model listed. Each model is created and provided by third parties. Models may not always be accurate or contextually appropriate. You are responsible for verifying the information before making important decisions. We are not liable for any damages, losses, or issues arising from its use, including data loss or inaccuracies in AI-generated content.

Downloads last month
9
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for inferencerlabs/Inkling-Mini-MLX-Q9

Quantized
(64)
this model