Hugging Face's logo

vamboai
/
morena-0.5b-mini-gguf

GGUF
african-languages
llama-cpp
isheanesu-misi
vambo-ai
conversational
Model card Files
xet
 Community
MORENA, an African foundation model

MORENA 0.5B mini, GGUF for llama.cpp

GGUF conversion of vamboai/morena-0.5b-mini, verified for logit equivalence against the safetensors weights. Read that model card first; everything in it, including the release status and the safety notes, applies unchanged. Converting the format changes none of it.

file size
morena-0.5b-mini-Q4_K_M.gguf 0.33 GB
morena-0.5b-mini-Q8_0.gguf 0.54 GB
morena-0.5b-mini-f16.gguf 1.01 GB

Chat turns use the reserved tokens <reserved_0> (user) and <reserved_1> (assistant):

llama-completion -m morena-0.5b-mini-f16.gguf -p "<reserved_0>\nNdeipi guta guru reZimbabwe?\n<reserved_1>\n" -e -n 64 --temp 0

Author and citation

Isheanesu Misi, Vambo AI. Trained on CINECA Leonardo, with support from the AI Hub for Sustainable Development.

@techreport{misi2026morena,
  title  = {MORENA: An African Foundation Model},
  author = {Misi, Isheanesu},
  institution = {Vambo AI},
  year   = {2026},
  month  = {September},
  note   = {Released 18 September 2026}
}

Licence

Apache 2.0. Commercial use is permitted, including fine-tuning and redistributing derivatives, under the terms of the licence.

The training corpus is not released with these weights.

Downloads last month
102
GGUF
Model size
0.5B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

4-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for vamboai/morena-0.5b-mini-gguf

Base model

vamboai/morena-1.5b-base
Finetuned
vamboai/morena-0.5b-mini
Quantized
(2)
this model

Datasets used to train vamboai/morena-0.5b-mini-gguf

Collection including vamboai/morena-0.5b-mini-gguf