Downloads · 30 days
97
34% of all-time downloads
theophilusowiti/AfriqueLlama-8B-Q4-K-M
AfriqueLlama-8B-Q4-K-M is a machine learning model from theophilusowiti. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Quantized version of McGill-NLP/AfriqueLlama-8B using llama.cpp with the Q4KM method (~4.5 bpw, mixed 4-bit K-quants).
Downloads · 30 days
97
34% of all-time downloads
All-time downloads
286
Public
Repo size
21 GB
Likes
0
Public
Click a slice to open those files.
.safetensors16.1 GB · 76%
From the Hugging Face model README
Quantized version of McGill-NLP/AfriqueLlama-8B
using llama.cpp with the Q4_K_M method (~4.5 bpw, mixed 4-bit K-quants).
llama-cli -m AfriqueLlama-8B-Q4_K_M.gguf -cnv -p "You are a helpful assistant"
Or load it directly in LM Studio or Ollama.
| Method | Bits/weight | Size (approx) |
|---|---|---|
| Q4_K_M | ~4.5 bpw | ~5 GB |