GGUF models by dhruvsangani
35 GGUF models quantized by dhruvsangani on Hugging Face. Sizes run from 1.1B to 8.03B parameters. The longest trained context is 128K tokens.
FE
FeatGPT_epochs10_2e 6 GGUF
Featgpt · dhruvsangani
Params1.24B
Context128K
Q4_K_M0.8 GB
FE
FeatGPT_part1 GGUF
Featgpt · dhruvsangani
Params1.24B
Context128K
Q4_K_M0.8 GB
FE
FeatGPT_part2 GGUF
Featgpt · dhruvsangani
Params1.24B
Context128K
Q4_K_M0.8 GB
LL
Featsystems Llama3.1 8b Lora GGUF
Llama · dhruvsangani
Params8.03B
Context128K
Q4_K_M4.9 GB
FE
FeatGPT_epochs50_2e 8 GGUF
Featgpt · dhruvsangani
Params1.24B
Context128K
Q4_K_M0.8 GB