OLMo-2-0425-1B-Instruct — GGUF (Q4_K_M)
AllenAI's own Q4_K_M GGUF, re-hosted with measured performance for the 1bit engine on Strix Halo.
Contents
OLMo-2-0425-1B-Instruct-Q4_K_M.gguf
Measured performance (Strix Halo, Vulkan)
pp512: 7652 tok/s · tg128: 215 tok/s
Running it
1bit serve -m OLMo-2-0425-1B-Instruct-Q4_K_M.gguf --device vulkan
Attribution
- Model and quantization: allenai/OLMo-2-0425-1B-Instruct-GGUF, Apache 2.0.
- License: Apache 2.0, inherited from the base model.
- Downloads last month
- 64
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/OLMo-2-0425-1B-Instruct-GGUF
Base model
allenai/OLMo-2-0425-1B Finetuned
allenai/OLMo-2-0425-1B-SFT Finetuned
allenai/OLMo-2-0425-1B-DPO Finetuned
allenai/OLMo-2-0425-1B-RLVR1 Finetuned
allenai/OLMo-2-0425-1B-Instruct