GGUF models by AlSamCur123

53 GGUF models quantized by AlSamCur123 on Hugging Face. Sizes run from 1.24B to 32.8B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
QU
Quen32
Quen · AlSamCur123
Params32.8B
Context—
Smallest15.6 GB
GGUF
MI
Mistral Nemo InstructContinuedFine
Mistral · AlSamCur123
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
DE
DeepSeek R1 Distill Llama 8B Unsloth Bnb 4bit
DeepSeek · AlSamCur123
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningTool use
MI
Mistral Nemo Base 2407 Uncensored
Mistral · AlSamCur123
Params12.2B
Context128K
Smallest7.1 GB
GGUF
LL
NotDolphin3.0 Llama3.1 8
Llama · AlSamCur123
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
GE
gemma 4 E4B ituncensored
Gemma · AlSamCur123
Params7.52B
Context128K
Q4_K_M5.3 GB
ReasoningVision
GE
gemma 4 26B A4B it
Gemma · AlSamCur123
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningVision
MI
Mistral Small3 24B Instruct
Mistral · AlSamCur123
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
MI
Mistral Small 24B Instruct 2501 Uncensored
Mistral · AlSamCur123
Params23.6B
Context32K
Smallest13.4 GB
GGUF
MI
Mistral Small Instruct 2409
Mistral · AlSamCur123
Params22.2B
Context128K
Q4_K_M13.3 GB
Tool use
MI
MistralBase37b
Mistral · AlSamCur123
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Llama3.2.3B
Llama · AlSamCur123
Params3.21B
Context128K
Smallest3.4 GB
Tool use
GE
gemma 4 31B it
Gemma · AlSamCur123
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningVision
MI
Ministral 8BContinuedFine
Mistral · AlSamCur123
Params8.02B
Context32K
Q4_K_M4.9 GB
Tool use
GE
gemma 4 E2B it
Gemma · AlSamCur123
Params4.65B
Context128K
Q4_K_M3.4 GB
ReasoningVision
MI
Mistral Nemo Instruct 2407 FineTune
Mistral · AlSamCur123
Params12.2B
Context128K
Smallest7.1 GB
Tool use
MI
DolphinMistral 24BContinuedFine
Mistral · AlSamCur123
Params23.6B
Context32K
Q4_K_M14.3 GB
Reasoning
MI
Mistral3InstructLogic
Mistral · AlSamCur123
Params7.25B
Context32K
Q4_K_M4.4 GB
Tool use
MI
Dolphin 2.9.3 Mistral 7B 32k
Mistral · AlSamCur123
Params7.25B
Context32K
Smallest4.1 GB
GGUF
MI
Mistral Nemo InstructContinuedFine
Mistral · AlSamCur123
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
MI
Mistral3UnslothExpimentalSettings
Mistral · AlSamCur123
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
MI
Mistral Small InstructContinuedFine
Mistral · AlSamCur123
Params22.2B
Context128K
Q4_K_M13.3 GB
Tool use
MI
Mistral 7b2ContinuedFine
Mistral · AlSamCur123
Params7.25B
Context32K
Q4_K_M4.4 GB
Tool use
MI
Mistral 24B
Mistral · AlSamCur123
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
MI
Mistral NeMo Minitron 8B InstructContinuedFine
Mistral · AlSamCur123
Params8.41B
Context31K
Q4_K_M5.1 GB
GGUF
NE
Nemo InstructContinuedFine
Nemo · AlSamCur123
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
MI
Mistral 3 7b R1
Mistral · AlSamCur123
Params7.25B
Context32K
Q4_K_M4.4 GB
ReasoningTool use
MI
NemoNew
Mistral · AlSamCur123
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
MI
Mistral 7B Instruct v0.3 Chatml
Mistral · AlSamCur123
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
EL
ElmerContinuedFine
Elmercontinuedfine · AlSamCur123
Params20B
Context31K
Q4_K_M12.0 GB
GGUF

About AlSamCur123 on Hugging Face

AlSamCur123 has published 53 GGUF models that ggufmodels.com tracks, across families such as Mistral, Llama and Gemma. The most downloaded are Quen32, Mistral Nemo InstructContinuedFine and DeepSeek R1 Distill Llama 8B Unsloth Bnb 4bit.

The quants AlSamCur123 publishes most often are Q4_0 (50), Q5_K_M (41), Q4_K_M (41) and Q8_0 (34). Their Q4_K_M files range from 0.8 to 18.7 GB. Parameter counts run from 1.24B to 32.8B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has AlSamCur123 published?

53 models are listed here, mainly from the Mistral, Llama and Gemma families. The most downloaded is Quen32.

Which quants does AlSamCur123 publish?

The most common are Q4_0 (50 models), Q5_K_M (41 models), Q4_K_M (41 models) and Q8_0 (34 models).

Keep browsing