NOTICE

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

INFORMATION

See GLM-4.7-REAP-268B MLX in action - demonstration video

Tested on a M3 Ultra 512GB RAM using Inferencer app

  • Single inference ~ tokens/s @ 1000 tokens
  • Batched inference ~ total tokens/s across three inferences
  • Memory usage: ~ GB

REAP-268B-q6.5bit quant achieved 1.53125 perplexity in our coding test against the Base-q9 model

Quantization Perplexity Token Accuracy Missed Divergence
Base-q3.9 1.33593 91.30% 27.11%
Base-q4.5 1.24218 94.65% 16.98%
Base-q5.5 1.21875 97.50% 9.994%
Base-q6.5 1.21875 98.30% 5.827%
REAP-218B-q6.5 1.88281 80.15% 47.17%
REAP-268B-q6.5 1.53125 86.85% 39.55%
Base-q9 1.21093 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 GLM-4.7-REAP-268B-A32B.

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
478
Safetensors
Model size
269B params
Tensor type
BF16
U32
F32
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for inferencerlabs/GLM-4.7-REAP-268B-A32B-MLX-6.5bit

Base model

zai-org/GLM-4.7
Quantized
(4)
this model