GGUF models by ijohn07

106 GGUF models quantized by ijohn07 on Hugging Face. Sizes run from 773M to 34.7B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
GE
Gemma 2 2b
Gemma · ijohn07
Params2.61B
Context8K
Smallest2.8 GB
GGUF
MA
MagpieLM 4B Chat v0.1 Q6 K
Magpielm · ijohn07
Params4.51B
Context128K
Smallest3.7 GB
GGUF
CH
Chocolatine 14B Instruct DPO v1.2 Q8 0
Chocolatine · ijohn07
Params14B
Context4K
Smallest14.8 GB
GGUF
DE
DeepSeek Coder V2 Lite Base
DeepSeek · ijohn07
Params15.7B
Context160K
Smallest16.7 GB
Coding
MI
Mistral Nemo Instruct 2407
Mistral · ijohn07
Params12.2B
Context128K
Smallest10.1 GB
Tool use
QW
Qwen2.5-1.5B-Open-R1-Distill
Qwen · ijohn07
Params1.54B
Context32K
Smallest1.6 GB
ReasoningTool use
OP
OpenCerebrum 2.0 7B Q8 0
Opencerebrum · ijohn07
Params7.24B
Context32K
Smallest7.7 GB
Coding
MI
Mistral Nemo Instruct 2407
Mistral · ijohn07
Params12.2B
Context1000K
Smallest13.0 GB
Tool use
DA
H2O Danube2 1.8b Chat
Danube · ijohn07
Params1.83B
Context8K
Smallest1.9 GB
GGUF
MI
Codestral 22B v0.1
Mistral · ijohn07
Params22.2B
Context32K
Smallest23.6 GB
Coding
YI
Yi 1.5 6B Chat
Yi · ijohn07
Params6.06B
Context4K
Smallest6.4 GB
GGUF
MA
MagpieLM 4B SFT v0.1 Q8 0
Magpielm · ijohn07
Params4.51B
Context128K
Smallest4.8 GB
GGUF
MI
Mistral Nemo Instruct 2407
Mistral · ijohn07
Params12.2B
Context1000K
Smallest4.8 GB
Tool use
LL
Apollo 0.4 Llama 3.1 8B
Llama · ijohn07
Params8.03B
Context128K
Smallest8.5 GB
GGUF
MI
Hercules 3.1 Mistral 7B Q8 0
Mistral · ijohn07
Params7.24B
Context32K
Smallest7.7 GB
Coding
AY
Aya 23 8B
Aya · ijohn07
Params8.03B
Context8K
Smallest3.4 GB
GGUF

Keep browsing