CorticalStack/mistral-7b-openhermes
An EXL2 6.5bpw quantised version of CorticalStack/mistral-7b-openhermes-sft.
An incomplete list of clients and libraries that are known to support EXL2:
- text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
- exllamav2, an inference library for running local LLMs on modern consumer GPUs.
- Downloads last month
- 0