This is an importance matrix (imatrix) generated from 1 million tokens for empero-ai/Qwythos-9B-v2.
During testing, the imatrix-quantized model significantly outperformed the standard quantized model.
It was generated using a patched version of llama-imatrix to properly respect chunking boundaries.
Chunking was performed at both 2048 and 16k.
- Downloads last month
- 17
Hardware compatibility
Log In to add your hardware
We're not able to determine the quantization variants.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for aney/Qwythos-9B-v2-imatrx-only
Base model
Qwen/Qwen3.5-9B-Base Finetuned
Qwen/Qwen3.5-9B Finetuned
empero-ai/Qwythos-9B-Claude-Mythos-5-1M Finetuned
empero-ai/Qwythos-9B-v2