This repository from the LM Studio community contains 8-bit quantized weights of Hermes-4-70B in MLX format for Apple silicon devices. It includes chat templates supporting advanced reasoning with optional <think> tags. The model is designed for local use with the MLX library, enabling high-performance inference on Macs without cloud dependency. It is intended for users exploring large open-source models on consumer Apple hardware.
Hermes 4 70B is a Foundation models & chat product. It focuses on running a large 70B parameter reasoning model efficiently on Macs using the MLX framework. It is built as an open-source project for developers with Apple hardware. Hermes 4 70B is open source under the MIT license. Hermes 4 70B is available on the command line.
lmstudio-community builds and maintains Hermes 4 70B, and the product first shipped in 2023. Development happens publicly on GitHub with 6.4k stars and 21 commits in the last 90 days. Key capabilities include Quantized Weights, MLX Format, and Apple Silicon Optimized.
Latest indexed changes and source events
lmstudio-community/Hermes-4-70B-MLX-8bit verified by the PulseGate indexer
Other apps tracked under the same category.
