inferencerlabs/LongCat-Flash-Thinking-2601-MLX-6.5bit

NOTICE

No longer available on HF due to storage restrictions - archived here

See LongCat-Flash-Thinking-2601 MLX in action - demonstration video

q6.5bit quant typically achieves 1.128 perplexity in our testing

Quantization	Perplexity
q2.5	41.293
q3.5	1.900
q4.5	1.168
q5.5	1.141
q6.5	1.128
q8.5	1.128

Usage Notes

Tested on a M3 Ultra 512GB RAM using Inferencer app v1.9.4

• Single inference ~20 tokens/s @ 1000 tokens
• Batched inference ~31 total tokens/s across two inferences
• Memory usage: ~437 GB
• For larger contexts use distributed compute or try the q5.5bit version

Quantized with a modified version of MLX

For more details see demonstration video or visit LongCat-Flash-Thinking-2601.

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.