Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Ollama
ModelsRuns open models such as gpt-oss, Qwen and DeepSeek on your own computer.
curl -fsSL https://ollama.com/install.sh | sh -
llama.cpp
ModelsThe C/C++ engine many local-model tools are built on. It runs models efficiently on ordinary hardware.
-
Qwen3.8-Flash-Next-FP4-Local
Modelsimage text to text model by nvidia · Model Optimizer
nvidia/Qwen3.8-Flash-Next-FP4-Local -
GLM-5.3-Flash-FP4-Local
Modelsimage text to text model by nvidia · Model Optimizer
nvidia/GLM-5.3-Flash-FP4-Local -
Inflect-Micro-v2
Modelstext to speech model by owensong
owensong/Inflect-Micro-v2 -
text generation model by yuxinlu1 · gguf
yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF -
text generation model by yuxinlu1 · gguf
yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF -
Phocinae-Largha-150M-v1
Modelstext classification model by Phocinae
Phocinae/Phocinae-Largha-150M-v1 -
OrcaCyber-Nano-1.0
Modelsimage text to text model by orcarouter · gguf
orcarouter/OrcaCyber-Nano-1.0 -
WVY-Blender-5m
Modelstext generation model by StarpowerTechnology · pytorch
StarpowerTechnology/WVY-Blender-5m -
Inflect-Mini-v3
Modelstext to speech model by owensong
owensong/Inflect-Mini-v3 -
text generation model by orcarouter · gguf
orcarouter/DeepSeek-V4.1-Flash-1017-abliterated-GGUF -
Flint-abliterated-GGUF
Modelstext generation model by orcarouter · gguf
orcarouter/Flint-abliterated-GGUF -
Ripple-65B-abliterated-GGUF
Modelstext generation model by orcarouter · gguf
orcarouter/Ripple-65B-abliterated-GGUF -
text generation model by FrostWolfAI · gguf
FrostWolfAI/Spark-X2.6-4B-abliterated-GGUF -
text generation model by orcarouter · gguf
orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF -
image text to text model by Jackrong · transformers
Jackrong/Qwopus3-5-9B-Coder-Flash-GGUF -
Qwen: Qwen3 Coder Next
ModelsQwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...
qwen/qwen3-coder-next
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.