Wolof-Llama-3.1-8B
Quantized Wolof LLM, Apache-2.0
Official site consultedAI: models
Last verified: 1 October 2026
GGUF quantized version of vonewman/Wolof-Llama-3.1-8B, an 8-billion-parameter Llama model. Twelve quantizations from 2 to 16 bits are offered (3.18 GB for Q2_K up to 16.1 GB for f16). They run locally with llama.cpp, Ollama or LM Studio. Apache 2.0 license.
Services
- Q4_K_S (4.69 GB) and Q4_K_M (4.92 GB), recommended
- Q8_0 (8.54 GB) and f16 for highest quality
- Local inference via llama.cpp, Ollama, LM Studio, Jan
Access requirements
Open files on Hugging Face, Apache 2.0 license; static quantizations only.
Sources
- Wolof-Llama-3.1-8B (new tab), verified on 1 October 2026Official site consulted