phi-2 — GGUF (Q4_K_M)
TheBloke's Q4_K_M GGUF, re-hosted with measured performance for the 1bit engine on Strix Halo.
Contents
phi-2.Q4_K_M.gguf
Measured performance (Strix Halo, Vulkan)
pp512: 3210 tok/s · tg128: 91.3 tok/s
Running it
1bit serve -m phi-2.Q4_K_M.gguf --device vulkan
Attribution
- Model: microsoft/phi-2, MIT.
- Quantization: TheBloke/phi-2-GGUF.
- License: MIT, inherited from the base model.
- Downloads last month
- 47
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/phi-2-GGUF
Base model
microsoft/phi-2