NOTICE

This language only version has been deprecated for the full edition available here: https://huggingface.co/inferencerlabs/Mistral-Small-4-119B-2603-MLX-9bit

INFORMATION

Tested on a M3 Ultra 512GB RAM using Inferencer app v1.10.7

  • Single inference ~ tokens/s @ 1000 tokens (figures coming soon)
  • Batched inference ~ total tokens/s across five inferences
  • Memory usage: ~126.8 GiB

q9bit quant typically achieves near lossless accuracy in our coding test

QuantizationPerplexityToken AccuracyMissed Divergence
q3.5168.043.45%72.57%
q4.51.3359391.65%27.61%
q4.81.2812593.75%21.15%
q5.51.2343795.05%17.28%
q6.51.2187596.95%12.03%
q8.51.2109397.55%10.50%
q91.2109397.55%10.50%
Base1.20312100.0%0.000%
Quantized with a modified version of MLX
For more details see demonstration video or visit Mistral-Small-4-119B-2603.

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
449
Safetensors
Model size
119B params
Tensor type
BF16
·
U32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support