GGUF models by paul-stansifer

47 GGUF models quantized by paul-stansifer on Hugging Face. Sizes run from 54M to 13B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
TI
qw us tinyllama 1b
Tinyllama · paul-stansifer
Params1.1B
Context2K
Smallest1.2 GB
GGUF
SM
qw3 smollm3 3b 1x2e 4
SmolLM · paul-stansifer
Params3.08B
Context64K
Q4_K_M1.9 GB
GGUF
LL
qw3 llama2 7b 1x2e 4
Llama · paul-stansifer
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
MI
qw orca 7b
Mistral · paul-stansifer
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
qw mistral 7b
Mistral · paul-stansifer
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GE
qw gemma2 2e 4x1 2b
Gemma · paul-stansifer
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
GE
qw gemma 4e 5x2 7b
Gemma · paul-stansifer
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
GE
qw3 gemma 7b 1x2e 4
Gemma · paul-stansifer
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
LL
qw llama3.1 2e 4x1 8b
Llama · paul-stansifer
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
GE
qw gemma 2e 4x1 7b
Gemma · paul-stansifer
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
PA
qw ds ll 2e 4x1 8b
Paul · paul-stansifer
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
qw shearedllama 2.7b
Llama · paul-stansifer
Params2.7B
Context4K
Q4_K_M1.6 GB
GGUF
GE
qw gemma 5e 4x1 7b
Gemma · paul-stansifer
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
GE
qw gemma2 1e 5x1 9b
Gemma · paul-stansifer
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
MI
qw3 mistralopenorca 7b 1x2e 4
Mistral · paul-stansifer
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
qw3 mistral0.1 7b 1x2e 4
Mistral · paul-stansifer
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
qw mistral high lr 7b
Mistral · paul-stansifer
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
qw mistral 2e 5x2 7b
Mistral · paul-stansifer
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
YI
Yi 1.5 9B
Yi · paul-stansifer
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
MI
qw3 gemma2 9b 1x6e 4
Mistral · paul-stansifer
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
GE
qwpl gemma 2e 4x1 7b 4e 5
Gemma · paul-stansifer
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
MI
qw mistral 1e 3 7b overfit
Mistral · paul-stansifer
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
qw us mistral 7b
Mistral · paul-stansifer
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
qw3 llama2 13b 1x2e 4
Llama · paul-stansifer
Params13B
Context4K
Smallest13.8 GB
GGUF
GE
qwpl gemma 7b 4x2e 5
Gemma · paul-stansifer
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
MI
qw mistral 4e 5x2 7b
Mistral · paul-stansifer
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
SM
qw smol 4e 5x1 1.7b
Smol · paul-stansifer
Params1.71B
Context2K
Q4_K_M1.1 GB
GGUF
MI
qw mistral 1e 3 7b
Mistral · paul-stansifer
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
qw shearedllama 4e 5x2 3b
Llama · paul-stansifer
Params2.7B
Context4K
Q4_K_M1.6 GB
GGUF
GE
qw gemma2 2e 5x2 9b
Gemma · paul-stansifer
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF

About paul-stansifer on Hugging Face

paul-stansifer has published 47 GGUF models that ggufmodels.com tracks, across families such as Mistral, Gemma and Llama. The most downloaded are qw us tinyllama 1b, qw3 smollm3 3b 1x2e 4 and qw3 llama2 7b 1x2e 4.

The quants paul-stansifer publishes most often are Q4_K_M (44), Q8_0 (23), Q2_K (21) and F16 (9). Their Q4_K_M files range from 1.1 to 5.8 GB. Parameter counts run from 54M to 13B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has paul-stansifer published?

47 models are listed here, mainly from the Mistral, Gemma and Llama families. The most downloaded is qw us tinyllama 1b.

Which quants does paul-stansifer publish?

The most common are Q4_K_M (44 models), Q8_0 (23 models), Q2_K (21 models) and F16 (9 models).

Keep browsing