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.

Most downloadedNewestLargestLongest contextSmallest
LL
Llama_UTK_Chatbot
Llama · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
Chem_train
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M5.2 GB
GGUF
GE
Anthro_train
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M5.2 GB
GGUF
GE
Agri R Gemma 2 2b 10e
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M5.2 GB
GGUF
LL
Llama 3 8b Instruct Bnb 4bit
Llama · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
gemma 2 2b bnb 4bit
Gemma · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
AAC_FT_allstructures
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M5.2 GB
GGUF
GE
Agri R Gemma 2 2b 3e
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M5.2 GB
GGUF
GE
Agri_train
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M5.2 GB
GGUF
LL
Llama 3 8b Instruct Bnb 4bit Optimal Library_Core
Llama · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
Anthro_ontologies_out
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M5.2 GB
GGUF
GE
Agri_train
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M5.2 GB
GGUF
GE
Anthro_Gemma_2_2b
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
GE
Agri_train4
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M5.2 GB
GGUF
LL
llama-3-8b-Instruct-bnb-4bit-demo
Llama · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Eloquent task 2025 llama 3 8b bnb 4bit
Llama · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 8b Instruct Bnb 4bit
Llama · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
llama 3 8b Instruct bnb 4bit robustness latest
Llama · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama_For_Library_Services
Llama · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 8b Instruct Bnb 4bit Library_Core
Llama · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
AAC_train4
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M5.2 GB
GGUF
GE
Agri R Gemma 2 2b
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M5.2 GB
GGUF
GE
Chem_ontologies_out
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M5.2 GB
GGUF
GE
Agri_ontologies_out
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M5.2 GB
GGUF
GE
Chem_Gemma_2_2b
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
GE
AAC 2E train
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M5.2 GB
GGUF
LL
llama 3 8b Instruct bnb 4bit base
Llama · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
llama 3 8b Instruct bnb 4bit robustness primary
Llama · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Voight kampff llama 3 8b bnb 4bit optimal
Llama · grohitraj
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
gemma2 FT epoch20
Gemma · grohitraj
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF

About grohitraj on Hugging Face

grohitraj has published 35 GGUF models that ggufmodels.com tracks, across families such as Gemma and Llama. The most downloaded are Llama_UTK_Chatbot, Chem_train and Anthro_train.

The quants grohitraj publishes most often are Q4_K_M (34) and F16 (18). Their Q4_K_M files range from 1.7 to 5.2 GB. Parameter counts run from 2.61B to 8.03B, and the longest trained context window is 8K tokens.

Frequently asked questions

What GGUF models has grohitraj published?

35 models are listed here, mainly from the Gemma and Llama families. The most downloaded is Llama_UTK_Chatbot.

Which quants does grohitraj publish?

The most common are Q4_K_M (34 models) and F16 (18 models).

Keep browsing