nsheth/ llama-3-lumimaid-8b-v0.1-iq-imatrix

3,768 2 years ago

It uses this one Q4_K_M-imat (4.89 BPW) quant for up to 12288 context sizes. for less than 8gb vram

vision

1 model

llama-3-lumimaid-8b-v0.1-iq-imatrix:latest
e3c3c83ca732 • 5.5GB • 8K context window •
Text input • 2 years ago