GGUF models by grohitraj
35 GGUF models quantized by grohitraj on Hugging Face. Sizes run from 2.61B to 8.03B parameters. The longest trained context is 8K tokens.
GE
Agri_Gemma_2_2b
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M1.7 GB
LL
Llama 3 8b Instruct Bnb 4bit Libcore
Llama · grohitraj
Params8.03B
Context8K
Smallest6.5 GB
LL
Lora_Test_Model2
Llama · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
Baseline_Llama3_8B_Fp16
Llama · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
llama 3 8b Instruct bnb 4bit vk optimal
Llama · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB