OpenELM-1.1B-Instruct — GGUF (Q4_K_M)
Community Q4_K_M GGUF for Apple's OpenELM, re-hosted with measured performance for the 1bit engine on Strix Halo.
Research use only — licensed under the Apple Machine Learning Research License, which restricts use to non-commercial scientific research and academic development. Commercial use, product development, or use in any commercial product/service is not permitted under this license.
Contents
OpenELM-1_1B-Instruct.Q4_K_M.gguf
Measured performance (Strix Halo, Vulkan)
pp512: 7356 tok/s · tg128: 234 tok/s
Running it
1bit serve -m OpenELM-1_1B-Instruct.Q4_K_M.gguf --device vulkan
Attribution
- Model: apple/OpenELM-1_1B-Instruct.
- Quantization: RichardErkhov/apple_-_OpenELM-1_1B-Instruct-gguf.
- Downloads last month
- 34
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for 1bit-MONSTER/OpenELM-1.1B-Instruct-GGUF
Base model
apple/OpenELM-1_1B-Instruct