Community GGUF quantizations and releases by webmp3. Independent, not official.
Sakura
webmp3
AI & ML interests
None yet
Recent Activity
updated a collection about 16 hours ago
Sakura (2) updated a collection about 17 hours ago
Sakura (2) updated a collection about 17 hours ago
SakuraOrganizations
None yet
Sakura Audio
Sakura Audio — compact local speech, ASR and TTS models optimized for practical CPU/edge inference.
Sakura Mini
Sakura Mini: noticeably smaller derivatives for high-end local machines.
-
webmp3/Sakura-Qwen3.8-27B-EfficientThink-GSQ-RCO-Hybrid
Text Generation • 27B • Updated • 236 • 3 -
webmp3/Sakura-FrogNano-4B-2609-GGUF
Image-Text-to-Text • 4B • Updated • 376 • 1 -
webmp3/Sakura-Fara1.5-9B-GGUF
Image-Text-to-Text • 9B • Updated • 370 • 1 -
webmp3/Sakura-Nanbeige4.2-3B-GGUF
Text Generation • 4B • Updated • 194 • 1
Sakura Media
Sakura image and video models: GGUF quantizations for stable-diffusion.cpp and llama.cpp (Qwen-Image, Iris, prompt rewriters; video models follow).
-
webmp3/Sakura-Qwen-Image-2.1-Turbo-GGUF
Text-to-Image • 7B • Updated • 728 -
webmp3/Sakura-Qwen-Image-2.1-Turbo-Uncensored-GGUF
Text-to-Image • 7B • Updated • 23.5k • 41 -
webmp3/Sakura-Iris-3B-GGUF
Text-to-Image • 3B • Updated • 532 • 2 -
webmp3/Sakura-Iris-3B-Uncensored-GGUF
Text-to-Image • 3B • Updated • 6.69k • 9
Sakura Micro
Sakura Micro: compact derivatives of large models for one local machine (e.g. 64 GB Strix Halo), with measured quality and speed.
-
webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO
Text Generation • 27B • Updated • 777 • 9 -
webmp3/Sakura-MiMo-V2.6-Flash-MOPD-P160-GGUF
Text Generation • 195B • Updated • 133 -
webmp3/Sakura-Qwen3.8-Flash-Next-Swift-3bit-352E-GGUF
Text Generation • 139B • Updated • 281 • 1 -
webmp3/Sakura-Qwen3.8-Flash-Next-Swift-2.5bit-352E-32GB-GGUF
Text Generation • 139B • Updated • 1.37k • 5
Sakura
Sakura: compressed releases close to the original model size and quality.
Sakura (2)
Community GGUF quantizations and releases by webmp3. Independent, not official.
Sakura Media
Sakura image and video models: GGUF quantizations for stable-diffusion.cpp and llama.cpp (Qwen-Image, Iris, prompt rewriters; video models follow).
-
webmp3/Sakura-Qwen-Image-2.1-Turbo-GGUF
Text-to-Image • 7B • Updated • 728 -
webmp3/Sakura-Qwen-Image-2.1-Turbo-Uncensored-GGUF
Text-to-Image • 7B • Updated • 23.5k • 41 -
webmp3/Sakura-Iris-3B-GGUF
Text-to-Image • 3B • Updated • 532 • 2 -
webmp3/Sakura-Iris-3B-Uncensored-GGUF
Text-to-Image • 3B • Updated • 6.69k • 9
Sakura Audio
Sakura Audio — compact local speech, ASR and TTS models optimized for practical CPU/edge inference.
Sakura Micro
Sakura Micro: compact derivatives of large models for one local machine (e.g. 64 GB Strix Halo), with measured quality and speed.
-
webmp3/Sakura-Micro-Bonsai-2-GSQ-RCO
Text Generation • 27B • Updated • 777 • 9 -
webmp3/Sakura-MiMo-V2.6-Flash-MOPD-P160-GGUF
Text Generation • 195B • Updated • 133 -
webmp3/Sakura-Qwen3.8-Flash-Next-Swift-3bit-352E-GGUF
Text Generation • 139B • Updated • 281 • 1 -
webmp3/Sakura-Qwen3.8-Flash-Next-Swift-2.5bit-352E-32GB-GGUF
Text Generation • 139B • Updated • 1.37k • 5
Sakura Mini
Sakura Mini: noticeably smaller derivatives for high-end local machines.
-
webmp3/Sakura-Qwen3.8-27B-EfficientThink-GSQ-RCO-Hybrid
Text Generation • 27B • Updated • 236 • 3 -
webmp3/Sakura-FrogNano-4B-2609-GGUF
Image-Text-to-Text • 4B • Updated • 376 • 1 -
webmp3/Sakura-Fara1.5-9B-GGUF
Image-Text-to-Text • 9B • Updated • 370 • 1 -
webmp3/Sakura-Nanbeige4.2-3B-GGUF
Text Generation • 4B • Updated • 194 • 1
Sakura
Sakura: compressed releases close to the original model size and quality.