inferencerlabs/Kimi-K2.6-MLX-3.6bit

NOTICE

This model has been superseded by the higher quality Q3.5-INF version available here

INFORMATION

See Kimi-K2.6 MLX in action - demonstration video

Tested on a M3 Ultra 512GB RAM using Inferencer app

• Single inference ~24.04 tokens/s @ 1000 tokens (debug build)
• Vision inference ~20.55 (available from v1.11.0)
• Memory usage: ~437 GiB

Q3.6 typically achieves useable accuracy in our coding test and fits within a 512GB memory budget

Quantization (bpw)	Perplexity	Token Accuracy	Missed Divergence	Size
Q3.5	1.1328125	94.92%	42.71%	450.19 GB
Q3.5-INF	1.078125	96.67%	22.04%	455.68 GB
Q3.6	1.1484375	94.72%	48.72%	470.99 GB
Base	Untested	100%	0.000%	658.59 GB

• Perplexity: Measures the confidence for predicting base tokens (lower is better)
• Token Accuracy: The percentage of correctly generated base tokens
• Missed Divergence: Measures severity of misses; how much the token was missed by

Quantized with a modified version of MLX

For more details see demonstration video or visit Kimi-K2.6.

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.