GGUF models by abubakar-muhammad

37 GGUF models quantized by abubakar-muhammad on Hugging Face. Sizes run from 135M to 3.21B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Llama 3.2 3b Paper Counterspeech Model Q4_K_M
Llama · abubakar-muhammad
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
GE
Gemma 2 2b Paper Counterspeech Model Q4_K_M
Gemma · abubakar-muhammad
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
LL
counterspeech model 3b test finetuned llama 3.2 16 bit
Llama · abubakar-muhammad
Params3.21B
Context128K
Smallest6.4 GB
Tool use
SM
SmolLm 1.7B Paper Counterspeech Model Q4_K_M
SmolLM · abubakar-muhammad
Params1.71B
Context2K
Q4_K_M1.1 GB
GGUF
GE
Gemma 2 2b
Gemma · abubakar-muhammad
Params2.61B
Context8K
Smallest2.8 GB
GGUF
GE
Gemma 2 2b
Gemma · abubakar-muhammad
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
SM
SmolLm 135M
SmolLM · abubakar-muhammad
Params135M
Context2K
Smallest0.3 GB
GGUF
SM
SmolLm 135M
SmolLM · abubakar-muhammad
Params135M
Context2K
Q4_K_M0.1 GB
GGUF
SM
SmolLm 1.7B Paper Counterspeech Model Q8_0
SmolLM · abubakar-muhammad
Params1.71B
Context2K
Smallest1.8 GB
GGUF
SM
SmolLm 360M
SmolLM · abubakar-muhammad
Params362M
Context2K
Q4_K_M0.3 GB
GGUF
SM
SmolLm 360M Paper Counterspeech Model 16bit Gguf
SmolLM · abubakar-muhammad
Params362M
Context2K
Smallest0.7 GB
GGUF
LL
Llama 3.2 1b
Llama · abubakar-muhammad
Params1.24B
Context128K
Smallest2.5 GB
GGUF
LL
counterspeech model 3b test finetuned llama 3.2
Llama · abubakar-muhammad
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
SM
SmolLm 1.7B
SmolLM · abubakar-muhammad
Params1.71B
Context2K
Smallest3.4 GB
GGUF
GE
Gemma 2 2b Paper Counterspeech Model 16bit Gguf
Gemma · abubakar-muhammad
Params2.61B
Context8K
Smallest5.2 GB
GGUF
LL
Llama 3.2 3b Paper Counterspeech Model Q8_0
Llama · abubakar-muhammad
Params3.21B
Context128K
Smallest3.4 GB
GGUF
SM
SmolLm 360M
SmolLM · abubakar-muhammad
Params362M
Context2K
Smallest0.4 GB
GGUF
SM
SmolLm 1.7B
SmolLM · abubakar-muhammad
Params1.71B
Context2K
Smallest1.8 GB
GGUF
SM
SmolLm 1.7B Paper Counterspeech Model 16bit Gguf
SmolLM · abubakar-muhammad
Params1.71B
Context2K
Smallest3.4 GB
GGUF
SM
SmolLm 360M Paper Counterspeech Model Q8_0
SmolLM · abubakar-muhammad
Params362M
Context2K
Smallest0.4 GB
GGUF
SM
SmolLm 360M Paper Counterspeech Model Q4_K_M
SmolLM · abubakar-muhammad
Params362M
Context2K
Q4_K_M0.3 GB
GGUF
SM
SmolLm 135M
SmolLM · abubakar-muhammad
Params135M
Context2K
Smallest0.1 GB
GGUF
SM
SmolLm 135M Paper Counterspeech Model Q8_0
SmolLM · abubakar-muhammad
Params135M
Context2K
Smallest0.1 GB
GGUF
LL
Llama 3.2 1b
Llama · abubakar-muhammad
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
SM
SmolLm 1.7B
SmolLM · abubakar-muhammad
Params1.71B
Context2K
Q4_K_M1.1 GB
GGUF
SM
SmolLm 360M
SmolLM · abubakar-muhammad
Params362M
Context2K
Smallest0.7 GB
GGUF
GE
Gemma 2 2b
Gemma · abubakar-muhammad
Params2.61B
Context8K
Smallest5.2 GB
GGUF
LL
Llama 3.2 3b Paper Counterspeech Model 16bit Gguf
Llama · abubakar-muhammad
Params3.21B
Context128K
Smallest6.4 GB
GGUF
GE
Gemma 2 2b Paper Counterspeech Model Q8_0
Gemma · abubakar-muhammad
Params2.61B
Context8K
Smallest2.8 GB
GGUF
SM
SmolLm 135M Paper Counterspeech Model Q4_K_M
SmolLM · abubakar-muhammad
Params135M
Context2K
Q4_K_M0.1 GB
GGUF

About abubakar-muhammad on Hugging Face

abubakar-muhammad has published 37 GGUF models that ggufmodels.com tracks, across families such as SmolLM, Llama and Gemma. The most downloaded are Llama 3.2 3b Paper Counterspeech Model Q4_K_M, Gemma 2 2b Paper Counterspeech Model Q4_K_M and counterspeech model 3b test finetuned llama 3.2 16 bit.

The quants abubakar-muhammad publishes most often are Q4_K_M (13), F16 (13), Q8_0 (12) and Q5_K_M (1). Their Q4_K_M files range from 0.1 to 2.0 GB. Parameter counts run from 135M to 3.21B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has abubakar-muhammad published?

37 models are listed here, mainly from the SmolLM, Llama and Gemma families. The most downloaded is Llama 3.2 3b Paper Counterspeech Model Q4_K_M.

Which quants does abubakar-muhammad publish?

The most common are Q4_K_M (13 models), F16 (13 models), Q8_0 (12 models) and Q5_K_M (1 models).

Keep browsing