Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
llama.cpp
ModelsThe C/C++ engine many local-model tools are built on. It runs models efficiently on ordinary hardware.
-
Haru-4B
Modelsaudio to audio model by higurashi-ai
higurashi-ai/Haru-4B -
harrier-oss-v1-0.6b
Modelsfeature extraction model by microsoft · sentence-transformers
microsoft/harrier-oss-v1-0.6b -
Qwen-2.5-1B-RLCD
Modelstext generation model by harshatheg · mlx
harshatheg/Qwen-2.5-1B-RLCD -
text classification model by j-hartmann · transformers
j-hartmann/emotion-english-distilroberta-base -
text generation model by dealignai · exllamav3
dealignai/DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw-UNCENSORED -
Gemma 4
ModelsOpen model that can run on your own hardware; reads text, images and audio.
-
Claude Fable 5.1
ModelsThe hardest reasoning and long-running work: multi-step decisions and projects that run for hours.
-
Gemini 4 Carbon
ModelsGoogle's most capable model, for hard software, maths and science problems and long multi-step agent work.
-
DeepSeek: DeepSeek V3.2
ModelsDeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
deepseek/deepseek-v3.2 -
Meta: Muse Glimmer 30B
ModelsMuse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...
meta/muse-glimmer-30b -
OpenAI: o3 Pro
ModelsThe o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...
openai/o3-pro -
Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...
meta/muse-glimmer-30b:batch -
Cohere: Command R+ (08-2024)
Modelscommand-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...
cohere/command-r-plus-08-2024 -
OpenAI: GPT-5.5
ModelsGPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...
openai/gpt-5.5 -
OpenAI: GPT-4.1 Mini
ModelsGPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...
openai/gpt-4.1-mini -
OpenAI: GPT-5.5 (batch)
ModelsGPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...
openai/gpt-5.5:batch -
OpenAI: GPT-4.1 Mini (batch)
ModelsGPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...
openai/gpt-4.1-mini:batch -
Auto Code
ModelsAuto Code is OpenRouter’s router built specifically for coding agents and harnesses. It uses the same routing engine as the [Auto Router](https://openrouter.ai/openrouter/auto), with every request treated as part of an...
openrouter/auto-code -
AionLabs: Aion-RP 1.0 (8B)
ModelsAion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...
aion-labs/aion-rp-llama-3.1-8b
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.