GGUF models by BenevolenceMessiah

75 GGUF models quantized by BenevolenceMessiah on Hugging Face. Sizes run from 137M to 32.8B parameters. The longest trained context is 986K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen2.5 Coder 7B
Qwen · BenevolenceMessiah
Params7.61B
Context32K
Smallest8.1 GB
CodingTool use
LL
Replete-Coder-Llama3-8B
Llama · BenevolenceMessiah
Params8.03B
Context8K
Smallest8.5 GB
CodingTool use
OL
OlympicCoder 7B Q8 0
Olympiccoder · BenevolenceMessiah
Params7.62B
Context32K
Smallest8.1 GB
CodingReasoningTool use
QW
QwQ 32B Preview
Qwen · BenevolenceMessiah
Params32.8B
Context32K
Smallest34.8 GB
ReasoningTool use
QW
QwQ 0.5B Distilled SFT
Qwen · BenevolenceMessiah
Params494M
Context32K
Smallest0.5 GB
ReasoningTool use
DE
DeepSeekR1 QwQ SkyT1 32B Fusion 811
DeepSeek · BenevolenceMessiah
Params32.8B
Context128K
Smallest34.8 GB
ReasoningTool use
DE
FuseO1 DeepSeekR1 QwQ SkyT1 32B Preview
DeepSeek · BenevolenceMessiah
Params32.8B
Context128K
Smallest34.8 GB
ReasoningTool use
QW
QwQ 32B Coder Fusion 9010
Qwen · BenevolenceMessiah
Params32.8B
Context32K
Smallest34.8 GB
CodingReasoningTool use
QW
Qwen2.5 14B Instruct 1M
Qwen · BenevolenceMessiah
Params14.8B
Context986K
Smallest15.7 GB
Tool use
RE
Reasoning TIES Coder v1.1 Q8 0
Reasoning · BenevolenceMessiah
Params32.8B
Context128K
Smallest34.8 GB
CodingReasoningTool use
DE
DeepCoder 1.5B Preview
Deepcoder · BenevolenceMessiah
Params1.78B
Context128K
Smallest1.9 GB
CodingTool use
LL
Llama-3-Instruct-8B-SPPO-Iter3
Llama · BenevolenceMessiah
Params8.03B
Context8K
Smallest8.5 GB
GGUF
QW
QwQ 32B Coder Fusion 9010
Qwen · BenevolenceMessiah
Params32.8B
Context32K
Smallest34.8 GB
CodingReasoningTool use
QW
QwQ 32B Preview
Qwen · BenevolenceMessiah
Params32.8B
Context32K
Smallest23.3 GB
ReasoningTool use
QW
Qwen 3 14B Enhanced v1.0 DARE TIES
Qwen · BenevolenceMessiah
Params1.56B
Context40K
Smallest1.7 GB
ReasoningTool use

Keep browsing