GGUF models by kholiavko

134 GGUF models quantized by kholiavko on Hugging Face. Sizes run from 559M to 14.7B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
reception test 2 guff
Llama · kholiavko
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
PH
test ph4
Phi · kholiavko
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
GE
test gemma 9b 22 10
Gemma · kholiavko
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
MI
Ministral 8B 30 10 25
Mistral · kholiavko
Params8.02B
Context32K
Smallest16.0 GB
GGUF
LL
reception 12 06 phones 2ep
Llama · kholiavko
Params8.03B
Context128K
Smallest8.5 GB
Tool use
MI
Ministral 8B Test
Mistral · kholiavko
Params8.02B
Context32K
Q4_K_M4.9 GB
GGUF
LL
reception llama 3.1 8b test 2
Llama · kholiavko
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
reception 12 07 6ep old struct
Llama · kholiavko
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
PH
phi 4
Phi · kholiavko
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
LL
reception llama 3.1 8b test 4
Llama · kholiavko
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
LL
reception test lora q4 k m GUFF
Llama · kholiavko
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
GE
test gemma 9b 24 10 reception
Gemma · kholiavko
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
TE
test nemo
Test · kholiavko
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
IN
intfloat multilingual e5 large instruct
Intfloat · kholiavko
Params559M
Context512
Smallest1.1 GB
GGUF
LL
test llama 3.2 3b
Llama · kholiavko
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
MI
Ministral 8B 28 09 25
Mistral · kholiavko
Params8.02B
Context32K
Smallest8.5 GB
GGUF
GE
test gemma 9b 25 10
Gemma · kholiavko
Params9.24B
Context8K
Smallest9.8 GB
GGUF
LL
reception llama 3.1 8b test 3
Llama · kholiavko
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
MI
Streaming Mistral 8b 26 06
Mistral · kholiavko
Params8.02B
Context32K
Q4_K_M4.9 GB
GGUF
LL
reception llama 3.1 8b test 4 1
Llama · kholiavko
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
RE
reception 12 06 v2 2 epochs
Reception · kholiavko
Params8.03B
Context128K
Smallest8.5 GB
Tool use
QW
Qwen3 8b Test Non Think
Qwen · kholiavko
Params8.19B
Context40K
Q4_K_M5.0 GB
Reasoning
LL
Streaming 22 06
Llama · kholiavko
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
RE
reception 29 11 4epochs
Reception · kholiavko
Params8.03B
Context128K
Smallest8.5 GB
Tool use
GE
test gemma 9b 24 10 chatml
Gemma · kholiavko
Params9.24B
Context8K
Smallest9.8 GB
GGUF
LL
reception 12 12 6ep old struct
Llama · kholiavko
Params8.03B
Context128K
Smallest5.7 GB
Tool use
LL
streaming 12 01
Llama · kholiavko
Params8.03B
Context128K
Smallest5.7 GB
Tool use
LL
streaming 9 01 7 ep
Llama · kholiavko
Params8.03B
Context128K
Smallest5.7 GB
Tool use
MI
Ministral 8B 13 08 25
Mistral · kholiavko
Params8.02B
Context32K
Smallest8.5 GB
GGUF
RE
reception nemo
Reception · kholiavko
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF

About kholiavko on Hugging Face

kholiavko has published 134 GGUF models that ggufmodels.com tracks, across families such as Llama, Reception and Mistral. The most downloaded are reception test 2 guff, test ph4 and test gemma 9b 22 10.

The quants kholiavko publishes most often are Q8_0 (104), Q5_K_M (48), Q4_K_M (47) and F16 (47). Their Q4_K_M files range from 1.6 to 8.9 GB. Parameter counts run from 559M to 14.7B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has kholiavko published?

134 models are listed here, mainly from the Llama, Reception and Mistral families. The most downloaded is reception test 2 guff.

Which quants does kholiavko publish?

The most common are Q8_0 (104 models), Q5_K_M (48 models), Q4_K_M (47 models) and F16 (47 models).

Keep browsing