Don't ask, for a hot minute it made sense. Only cost about 30-ish cents on 3x A100s with 80GB of VRAM each and a context of 32k.

Downloads last month
20
Safetensors
Model size
4B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for owenqwenllmwine/phi4-codex

Finetuned
(26)
this model
Quantizations
1 model

Dataset used to train owenqwenllmwine/phi4-codex