inferencerlabs/GLM-5.1-MLX-4.8bit

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)	Perplexity	Token Accuracy	Missed Divergence
q4.5	1.35937	89.75%	28.98%
q4.8	1.26562	93.50%	19.57%
q5.5	1.24218	94.60%	17.55%
q6.5	1.21875	96.85%	16.03%
q8.5	1.21875	97.65%	9.92%
q9	1.21093	97.95%	9.61%
Base	1.20312	100.0%	0.000%

• 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 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.