GGUF models by cortexso

54 GGUF models quantized by cortexso on Hugging Face. Sizes run from 988M to 72.7B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
DE
deepseek r1
DeepSeek · cortexso
Params70.6B
Context128K
Q4_K_M1.1 GB
Reasoning
LL
llama3.2
Llama · cortexso
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
CO
cogito v1
Cogito · cortexso
Params3.61B
Context128K
Q4_K_M2.2 GB
ReasoningTool use
MI
mistral small 24b
Mistral · cortexso
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
GE
gemma3
Gemma · cortexso
Params11.8B
Context32K
Q4_K_M0.8 GB
GGUF
OL
olmo 2
OLMo · cortexso
Params32.2B
Context4K
Q4_K_M4.5 GB
GGUF
PH
phi 4 reasoning
Phi · cortexso
Params3.84B
Context128K
Q4_K_M2.5 GB
ReasoningTool use
SA
sailor 2
Sailor · cortexso
Params988M
Context4K
Q4_K_M0.7 GB
GGUF
QW
qwen2.5 coder
Qwen · cortexso
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
MI
Codestral 22B v0.1
Mistral · cortexso
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
DE
deepseek r1 distill qwen 1.5b
DeepSeek · cortexso
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
GE
gemma2
Gemma · cortexso
Params27.2B
Context8K
Q4_K_M1.7 GB
GGUF
LL
Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps
Llama · cortexso
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
AY
aya
Aya · cortexso
Params35B
Context8K
Q4_K_M5.1 GB
GGUF
QW
qwen2
Qwen · cortexso
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
IN
intellect 2
Intellect · cortexso
Params32.8B
Context40K
Q4_K_M19.9 GB
ReasoningTool use
LL
llama3.1
Llama · cortexso
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
MI
mistral nemo
Mistral · cortexso
Params12.2B
Context128K
Q4_K_M7.5 GB
Tool use
DE
deepseek r1 distill qwen 14b
DeepSeek · cortexso
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
TI
tinyllama
Tinyllama · cortexso
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
CO
command r
Command R · cortexso
Params32.3B
Context128K
Q4_K_M19.8 GB
GGUF
DE
deepseek r1 distill qwen 32b
DeepSeek · cortexso
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
MA
marco o1
Marco · cortexso
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
DE
deepseek r1 distill qwen 7b
DeepSeek · cortexso
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
LL
Llama 3.1 Tulu 3 8B SFT
Llama · cortexso
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
llama3
Llama · cortexso
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
SI
simplescaling s1
Simplescaling · cortexso
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
PH
Phi 3.5 Mini Instruct
Phi · cortexso
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
OP
openhermes 2.5
Openhermes · cortexso
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
OP
opencoder
Opencoder · cortexso
Params7.77B
Context8K
Q4_K_M4.7 GB
Coding

About cortexso on Hugging Face

cortexso has published 54 GGUF models that ggufmodels.com tracks, across families such as DeepSeek, Qwen and Llama. The most downloaded are deepseek r1, llama3.2 and cogito v1.

The quants cortexso publishes most often are Q4_K_M (52), Q8_0 (48), Q6_K (48) and Q5_K_S (48). Their Q4_K_M files range from 0.7 to 47.4 GB. Parameter counts run from 988M to 72.7B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has cortexso published?

54 models are listed here, mainly from the DeepSeek, Qwen and Llama families. The most downloaded is deepseek r1.

Which quants does cortexso publish?

The most common are Q4_K_M (52 models), Q8_0 (48 models), Q6_K (48 models) and Q5_K_S (48 models).

Keep browsing