GGUF models by roleplaiapp

1023 GGUF models quantized by roleplaiapp on Hugging Face. Sizes run from 6M to 72.7B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
JA
JapMed SLERP Q8 0
Japmed · roleplaiapp
Params8.03B
Context8K
Smallest8.5 GB
GGUF
DE
DeepSeek R1 Distill Alpaca FineTuned Q6 K
DeepSeek · roleplaiapp
Params8.03B
Context128K
Smallest6.6 GB
ReasoningTool use
DE
DeepSky T100 Q2 K
Deepsky · roleplaiapp
Params32.8B
Context128K
Smallest12.3 GB
Tool use
QW
Qwen2.5 32B Instruct
Qwen · roleplaiapp
Params32.8B
Context32K
Smallest18.8 GB
ReasoningTool use
YU
YuE s1 7B anneal en cot Q5 K M
Yue · roleplaiapp
Params6.22B
Context16K
Smallest4.4 GB
GGUF
SI
SILMA Kashif 2B Instruct v1.0
Silma · roleplaiapp
Params2.61B
Context12K
Smallest1.4 GB
GGUF
SI
SILMA Kashif 2B Instruct v1.0
Silma · roleplaiapp
Params2.61B
Context12K
Smallest1.9 GB
GGUF
LL
Llama3.2 doker Q6 K
Llama · roleplaiapp
Params1.24B
Context128K
Smallest1.0 GB
Tool use
JA
Jaja small v1 Q4 K M
Jaja · roleplaiapp
Params362M
Context8K
Q4_K_M0.3 GB
GGUF
LL
Reasoning Llama 3.1 CoT RE1 Q2 K
Llama · roleplaiapp
Params8.03B
Context128K
Smallest3.2 GB
ReasoningTool use
LL
DeepSauerHuatuoSkywork R1 O1 Llama 3.1 8B
Llama · roleplaiapp
Params8.03B
Context128K
Smallest6.6 GB
Reasoning
QW
Qwen2.5-1.5B-Open-R1-Distill
Qwen · roleplaiapp
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
LL
DeepSauerHuatuoSkywork R1 O1 Llama 3.1 8B
Llama · roleplaiapp
Params8.03B
Context128K
Q4_K_M4.9 GB
Reasoning
DE
DeepSeek R1 Distill Qwen 32B Japanese
DeepSeek · roleplaiapp
Params32.8B
Context128K
Smallest14.4 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 14B Japanese
DeepSeek · roleplaiapp
Params14.8B
Context128K
Smallest7.3 GB
ReasoningTool use
QW
Qwen2.5 7B Instruct 1M
Qwen · roleplaiapp
Params7.62B
Context986K
Smallest3.3 GB
Tool use
DE
DeepSky T100 Q6 K
Deepsky · roleplaiapp
Params32.8B
Context128K
Smallest26.9 GB
Tool use
DE
DeepSky T100 IQ4 XS
Deepsky · roleplaiapp
Params32.8B
Context128K
Smallest17.9 GB
Tool use
QW
Qwen2.5 32B Instruct
Qwen · roleplaiapp
Params32.8B
Context32K
Smallest17.7 GB
ReasoningTool use
QW
Qwen2.5 32B Instruct
Qwen · roleplaiapp
Params32.8B
Context32K
Smallest15.9 GB
ReasoningTool use
DE
Qwen2.5 32B DeepSeek R1 Instruct i1 IQ4 XS
DeepSeek · roleplaiapp
Params32.8B
Context32K
Smallest17.7 GB
ReasoningTool use
YU
YuE s1 7B anneal en cot Q8 0
Yue · roleplaiapp
Params6.22B
Context16K
Smallest6.6 GB
GGUF
NE
L3.3 Nevoria R1 70b Q8 0
Nevoria · roleplaiapp
Params38B
Context128K
Smallest39.9 GB
Reasoning
NE
L3.3 Nevoria R1 70b IQ3 M
Nevoria · roleplaiapp
Params70.6B
Context128K
Smallest31.9 GB
ReasoningTool use
ME
medicine LLM Q2 K
Medicine · roleplaiapp
Params6.74B
Context2K
Smallest2.5 GB
GGUF
ME
medicine LLM Q3 K L
Medicine · roleplaiapp
Params6.74B
Context2K
Smallest3.6 GB
GGUF
OP
OpenThinker 7B Q6 K
Openthinker · roleplaiapp
Params7.62B
Context32K
Smallest6.3 GB
Tool use
DE
DeepSeek R1 Distill Qwen 14B Japanese
DeepSeek · roleplaiapp
Params14.8B
Context128K
Smallest10.5 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 32B Japanese
DeepSeek · roleplaiapp
Params32.8B
Context128K
Smallest23.3 GB
ReasoningTool use
CO
Confucius O1 14B
Confucius · roleplaiapp
Params14.8B
Context32K
Smallest6.4 GB
Tool use

Keep browsing