Resource directory
Find what you need for your workflow.
Guides: techniques, setup, and troubleshootingSearch Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
All resources
19 shown of 32,999
Gemma 4 E2B It RotorQuant MLX 2bit
> [!TIP] > KV-cache quantization without any fork (recommended, 2026): upstream > llama.cpp/Ollama now cover this natively — use -ctk q80 -ctv q80 > (half KV memory, negligible quality loss: perplexity +0.002–0.05)...
Scallop Yolo26x Lr 1280 Aug
Zoo ID: det-scallopyolo26xlr1280aug · canonical weights: best.pt (training epoch 50)
model.safetensors
罗比菈塔 Robert Granter of Colors.safetensors
70s Sci-Fi Movie
Cohere Transcribe Arabic 07 2026 Int4
A memory-efficient INT4 (NF4) quantization of CohereLabs/cohere-transcribe-arabic-07-2026, Cohere Labs' 2B-parameter Arabic/English speech-recognition model. Produced with bitsandbytes NF4 4-bit with double...
Cowgirl_position_low_noise.safetensors
model.safetensors
Mistral Nemo Instruct 2407 Heretic Noslop GGUF
These are quantizations of the model Mistral-Nemo-Instruct-2407-heretic-noslop, with an imatrix from bartowski
realDream_fluxDevV3.safetensors
noheelsstrap_tempe.safetensors
model.safetensors
HARUKI_MIX
Trajtok Trajvitv2
TrajViT-v2 wraps the TrajTok-v2 segmenter with a ViT-Large transformer and trains it under a CLIP-style image-text contrastive objective. Trajectory tokens (K=128 per clip from the segmenter) are contextualised by a...
6a5025f3680854887e2b5210.safetensors
画风 きんく style 【anima】
This model doesn't need a trigger word
