NOTICE

CURRENTLY UPLOADING...     CURRENTLY UPLOADING...     CURRENTLY UPLOADING...

See GLM-5.1 MLX in action - demonstration video

Tested on a M3 Ultra 512GB RAM using Inferencer app

  • Single inference ~16.9 tokens/s @ 1000 tokens (debug build)
  • Batched inference ~22.8 total tokens/s across two inferences
  • Memory usage: ~420.61 GiB

4.8bpw quant typically achieves 93% accuracy in our coding test

Quantization (bpw)PerplexityToken AccuracyMissed Divergence
q4.51.3593789.75%28.98%
q4.81.2656293.50%19.57%
q5.51.2421894.60%17.55%
q6.51.2187596.85%16.03%
q8.51.2187597.65%9.92%
q91.2109397.95%9.61%
Base1.20312100.0%0.000%
Quantized with a modified version of MLX
For more details see demonstration video or visit zai-org/GLM-5.1.

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
1,091
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Nishant2414/GLM-5.1-MLX-4.8bit

Base model

zai-org/GLM-5.1
Quantized
(26)
this model