GGUF models by prabal123

36 GGUF models quantized by prabal123 on Hugging Face. Sizes run from 1.1B to 6.91B parameters. The longest trained context is 4K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
NR llama2 LogR Cust data q4 0 q4 k m
Llama · prabal123
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
NO
Nous research finetuned 1Epoch
Nous · prabal123
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
TI
Tinyllama 150 50 200 210epoch f32
Tinyllama · prabal123
Params1.1B
Context2K
Smallest4.4 GB
GGUF
LL
Meta llama nl sql llamaformat 5Epoch
Llama · prabal123
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
ME
Metallama Noaccountnum 5 plus 1 EPOCH 2
Metallama · prabal123
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
OR
Original Metallama 5Epoch Graphofloss
Original · prabal123
Params6.74B
Context4K
Smallest4.2 GB
GGUF
LL
Open_Llama_3B
Llama · prabal123
Params3.43B
Context2K
Smallest3.6 GB
GGUF
ME
Metallama Noaccountnum 1dot7 EPOCH 3
Metallama · prabal123
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
ME
Metallama Noaccountnum 1dot7and4 EPOCH 3
Metallama · prabal123
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
OR
Original Metallama 6Epoch Graphofloss 2
Original · prabal123
Params6.74B
Context4K
Smallest3.3 GB
GGUF
TI
Tinyllama 1 q8 bit
Tinyllama · prabal123
Params1.1B
Context2K
Smallest1.2 GB
GGUF
TI
Tinyllama 2 f32bit
Tinyllama · prabal123
Params1.1B
Context2K
Smallest4.4 GB
GGUF
OP
Openllama 3B NL SQL8E LR2 DIV 2
Openllama · prabal123
Params3.43B
Context2K
Smallest3.6 GB
GGUF
LL
Llama nl sql2
Llama · prabal123
Params6.74B
Context4K
Smallest7.2 GB
GGUF
OP
Openllama 50Epoch F16
Openllama · prabal123
Params3.43B
Context2K
Smallest6.9 GB
GGUF
LL
Llama nl sql 3
Llama · prabal123
Params6.74B
Context4K
Smallest7.2 GB
GGUF
LL
Open_Llama_3B
Llama · prabal123
Params3.43B
Context2K
Smallest6.9 GB
GGUF
TI
Tinyllama 80Epoch f32 Propertrainingformat
Tinyllama · prabal123
Params1.1B
Context2K
Smallest4.4 GB
GGUF
OP
Openllama 3B NL SQL8E LR2 DIV 2 f16
Openllama · prabal123
Params3.43B
Context2K
Smallest6.9 GB
GGUF
TI
tinyllama 80 2Epoch Rank128 trainingAlpacaformat
Tinyllama · prabal123
Params1.1B
Context2K
Smallest4.4 GB
GGUF
ME
Metallama Noaccount num 10Epoch
Metallama · prabal123
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
LL
Llama nl sql 4
Llama · prabal123
Params6.91B
Context4K
Smallest7.3 GB
GGUF
TI
tinyllama 20epoch f32
Tinyllama · prabal123
Params1.1B
Context2K
Smallest4.4 GB
GGUF
TI
Tinyllama 150epoch f32
Tinyllama · prabal123
Params1.1B
Context2K
Smallest4.4 GB
GGUF
TI
Tinyllama 150epoch f16
Tinyllama · prabal123
Params1.1B
Context2K
Smallest2.2 GB
GGUF
TI
Tinyllama 150 50 200epoch f32
Tinyllama · prabal123
Params1.1B
Context2K
Smallest4.4 GB
GGUF
TI
Tinyllama 150 50 200 210 80epoch f32
Tinyllama · prabal123
Params1.1B
Context2K
Smallest4.4 GB
GGUF
OP
Openllama 1Epoch f16
Openllama · prabal123
Params3.43B
Context2K
Smallest6.9 GB
GGUF
TI
Tinyllama 150 50 20Epoch F32 FINAL
Tinyllama · prabal123
Params1.1B
Context2K
Smallest4.4 GB
GGUF
NO
Nous Research 1Epoch q8
Nous · prabal123
Params6.74B
Context4K
Smallest7.2 GB
GGUF

About prabal123 on Hugging Face

prabal123 has published 36 GGUF models that ggufmodels.com tracks, across families such as Tinyllama, Llama and Openllama. The most downloaded are NR llama2 LogR Cust data q4 0 q4 k m, Nous research finetuned 1Epoch and Tinyllama 150 50 200 210epoch f32.

The quants prabal123 publishes most often are Q4_K_M (10), Q4_0 (3), Q4_1 (2) and Q3_K_M (2). Their Q4_K_M files range from 4.1 to 4.1 GB. Parameter counts run from 1.1B to 6.91B, and the longest trained context window is 4K tokens.

Frequently asked questions

What GGUF models has prabal123 published?

36 models are listed here, mainly from the Tinyllama, Llama and Openllama families. The most downloaded is NR llama2 LogR Cust data q4 0 q4 k m.

Which quants does prabal123 publish?

The most common are Q4_K_M (10 models), Q4_0 (3 models), Q4_1 (2 models) and Q3_K_M (2 models).

Keep browsing