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
| Quantization | Perplexity | Token Accuracy | Missed Divergence |
|---|---|---|---|
| q3.5 | 168.0 | 43.45% | 72.57% |
| q4.5 | 1.33593 | 91.65% | 27.61% |
| q4.8 | 1.28125 | 93.75% | 21.15% |
| q5.5 | 1.23437 | 95.05% | 17.28% |
| q6.5 | 1.21875 | 96.95% | 12.03% |
| q8.5 | 1.21093 | 97.55% | 10.50% |
| q9 | 1.21093 | 97.55% | 10.50% |
| Base | 1.20312 | 100.0% | 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