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.
QW
qwen qwq
Qwen · cortexso
Params32.8B
Context128K
Q4_K_M19.9 GB
SM
small thinker
Small · cortexso
Params3.4B
Context32K
Q4_K_M2.1 GB
DE
deepseek r1 distill llama 8b
DeepSeek · cortexso
Params8.03B
Context128K
Q4_K_M4.9 GB
SK
sky t1
Sky · cortexso
Params32.8B
Context32K
Q4_K_M19.9 GB
QW
qwen3 deepresearch nothink
Qwen · cortexso
Params14.8B
Context40K
Q4_K_M9.0 GB
DE
DeepScaleR 1.5B Preview
Deepscaler · cortexso
Params1.78B
Context128K
Q4_K_M1.1 GB
FA
falcon3
Falcon · cortexso
Params10.3B
Context32K
Q4_K_M6.3 GB
MI
mistral
Mistral · cortexso
Params7.25B
Context32K
Q4_K_M4.4 GB
SM
smollm2
SmolLM · cortexso
Params1.71B
Context8K
Q4_K_M1.1 GB
IN
internlm3 8b it
InternLM · cortexso
Params8.8B
Context32K
Q4_K_M5.4 GB
QW
qwq
Qwen · cortexso
Params32.8B
Context32K
Q4_K_M19.9 GB
AY
aya expanse
Aya · cortexso
Params32.3B
Context8K
Q4_K_M5.1 GB
YI
yi 1.5
Yi · cortexso
Params34.4B
Context4K
Q4_K_M20.7 GB
PH
phi 4
Phi · cortexso
Params14.7B
Context16K
Q4_K_M9.1 GB
GE
gemma
Gemma · cortexso
Params8.54B
Context8K
Q4_K_M5.3 GB
GR
granite 3.2 it
Granite · cortexso
Params8.17B
Context128K
Q4_K_M4.9 GB
IN
INTELLECT 1 Instruct
Intellect · cortexso
Params10.2B
Context8K
Q4_K_M6.2 GB
QW
qwen3 4b v0.3 deepresearch no think
Qwen · cortexso
Params4.02B
Context40K
Q4_K_M2.5 GB
LL
llava v1.6
LLaVA · cortexso
Params6.74B
Context4K
Smallest4.1 GB
DE
deepseek r1 distill llama 70b
DeepSeek · cortexso
Params70.6B
Context128K
Q4_K_M42.5 GB
LL
llama3.3
Llama · cortexso
Params70.6B
Context128K
Q4_K_M42.5 GB
LL
llava
LLaVA · cortexso
Params7.24B
Context32K
Q4_K_M4.4 GB
AT
Athene V2 Chat
Athene · cortexso
Params72.7B
Context32K
Q4_K_M47.4 GB
MI
mistralai_mixtral-8x7b-v0.1
Mistral · cortexso
Params46.7B
Context32K
Smallest26.4 GB