All 109 ai models & local execution tools in the catalog across 8 sub-categories, ordered free tiers first.
Flocci AI Tools lists 109 of them, ordered free tiers first: Arize Phoenix, DeepSeek Models, Design Arena, Epoch AI and ERNIE 4.5 Open Models (Baidu). 103 of the 109 are free or have a free tier. Each entry states what it uniquely does rather than a score.
76 on this page are marked fully free with no paid plan at all: Arize Phoenix, DeepSeek Models, Design Arena, Epoch AI and ERNIE 4.5 Open Models (Baidu). The remaining 33 are freemium, trial or paid, and each is labelled with its exact tier so nothing surprises you at sign-up.
Free tools first, then freemium, then trial, then paid, and alphabetically inside each tier. Nobody pays to appear higher: Flocci AI Tools carries no ads, no sponsored slots and no paid listings, so the order reflects price and nothing else.
Arize Phoenix, DeepSeek Models, Design Arena, Epoch AI and ERNIE 4.5 Open Models (Baidu) all work in a browser tab with no install needed — just open the site and go. 50 of the 103 free AI Models & Local Execution Tools listed here are browser-based.
Google Stax, Qwen (Alibaba), Google AI Studio, Langfuse and OpenRouter support Google sign-in, so you can start without creating a new account. That's 5 of the 103 free AI Models & Local Execution Tools on this page.
DeepSeek Models, Qwen (Alibaba), sherpa-onnx, AnythingLLM and Google AI Edge Gallery have an iOS or Android app. 11 of the 103 free AI Models & Local Execution Tools here can run on your phone.
AnythingLLM, Axolotl, BitNet, DeepEval and EleutherAI LM Evaluation Harness can be self-hosted or run locally without a browser — useful for privacy, air-gapped networks, or avoiding API rate limits. 39 of the 103 free AI Models & Local Execution Tools here run offline.
| Tool | Pricing | Type | Listed for |
|---|---|---|---|
| Arize Phoenix | Free | LLM Eval & Observability | Fully open-source, self-hostable with zero setup via `uvx` (pip/conda also supported) |
| DeepSeek Models | Free | Notable Open Models | DeepSeek V4-Pro and V4-Flash open-weight MoE models, MIT-licensed |
| Design Arena | Free | Leaderboards & Benchmarks | Crowdsourced Bradley-Terry (Elo-style) ranking of AI models specifically on design/aesthetic quality, not raw capability |
| Epoch AI | Free | Leaderboards & Benchmarks | Independent, non-vendor research institute tracking AI compute, training cost and capability trends over time |
| ERNIE 4.5 Open Models (Baidu) | Free | Notable Open Models | ERNIE-4.5 family including 21B-A3B Thinking and VL-424B-A47B multimodal MoE |
| Falcon (TII) | Free | Notable Open Models | Falcon-H1 hybrid Transformer-Mamba family for efficient long-context inference |
| Google Stax | Free | LLM Eval & Observability | Build evals with human raters or LLM autoraters on your own data |
| Hunyuan (Tencent) | Free | Notable Open Models | Open-weight Hunyuan Hy3 and Hy4-preview flagship text models |
| Laminar | Free | LLM Eval & Observability | Open-source observability and evals platform for AI agents (Apache-2.0) |
| LiveBench | Free | Leaderboards & Benchmarks | Continuously refreshed questions to avoid benchmark contamination |
| LLaMA-Factory | Free | Fine-Tuning & Training Frameworks | Zero-code Web UI (LLaMA Board) for fine-tuning 100+ open models without writing training scripts |
| LMArena (Arena.ai) | Free | Leaderboards & Benchmarks | Crowd-voted 'Battle Mode' blind head-to-head comparisons across text, image, and coding/agent models |
| MiniMax M2 (open weights) | Free | Notable Open Models | MiniMax's open-weight M-series: M3 multimodal MoE with very long context, plus M2.x agentic-coding checkpoints |
| Mistral Open Models (Magistral, Devstral, Voxtral) | Free | Notable Open Models | Open-weight Mistral Medium 3.5, Small 4 and Large 3 general models |
| NVIDIA Canary-Qwen 2.5B | Free | Speech & Transcription Engines | Speech-recognition plus LLM hybrid model that transcribes and can summarize or answer questions about audio |
| NVIDIA Cosmos | Free | Robotics & Embodied AI | Open platform of world foundation models, datasets and tools for physical AI |
| NVIDIA Parakeet | Free | Speech & Transcription Engines | Tops the Hugging Face Open ASR Leaderboard with 6.05% average WER at 0.6B params |
| OLMo (Ai2) | Free | Notable Open Models | Only major model family shipping full pretraining data (Dolma), code and intermediate checkpoints, not just weights |
| Open ASR Leaderboard (Hugging Face) | Free | Leaderboards & Benchmarks | Ranks speech-recognition models by word error rate and real-time speed across English and multilingual sets |
| Qwen (Alibaba) | Free | Notable Open Models | Open Qwen3.x family from phone-sized to multi-trillion-parameter MoE, Apache 2.0 |
| Seed-OSS (ByteDance) | Free | Notable Open Models | Seed-OSS-36B open reasoning LLM with native 512K-token context, Apache 2.0 |
| sherpa-onnx | Free | Speech & Transcription Engines | Offline speech-to-text, text-to-speech, VAD and speaker diarization without internet |
| Step (StepFun) | Free | Notable Open Models | Step-3.7-Flash open multimodal model with FP8, NVFP4 and GGUF builds |
| SWE-bench | Free | Leaderboards & Benchmarks | The standard benchmark for evaluating autonomous coding agents on real GitHub issue resolution |
| Xiaomi MiMo | Free | Notable Open Models | MiMo-V2.6-Pro (1T parameters) and V2.6-Flash (311B) open-weight reasoning and agent models |
| AI Toolkit (Ostris) | Free | Fine-Tuning & Training Frameworks | All-in-one trainer for LoRAs on diffusion and video models (FLUX, Wan and more) |
| AnythingLLM | Free | Local LLM Runners | All-in-one local RAG and agents app |
| Axolotl | Free | Fine-Tuning & Training Frameworks | Config-file-driven fine-tuning workflow (YAML) covering LoRA, QLoRA, full fine-tuning, preference tuning and RL |
| BitNet | Free | Local LLM Runners | Official inference framework for 1-bit (ternary) LLMs |
| DeepEval | Free | LLM Eval & Observability | Open-source LLM evaluation framework with pytest-style tests and 50+ metrics |
| EleutherAI LM Evaluation Harness | Free | LLM Eval & Observability | Standard open framework for running hundreds of benchmarks (MMLU, GSM8K and more) against any LLM |
| EXAONE (LG AI Research) | Free | Notable Open Models | EXAONE 4.5: LG's first open-weight vision-language model for industrial use cases |
| exo | Free | Local LLM Runners | Links everyday devices (Macs, PCs, phones) into one cluster to run models too large for a single machine |
| faster-whisper | Free | Speech & Transcription Engines | Whisper reimplementation on CTranslate2, up to 4x faster with less memory |
| FunASR | Free | Speech & Transcription Engines | Open-source speech recognition toolkit with Paraformer and SenseVoice models |
| Gemma (Google) | Free | Notable Open Models | Google's lightweight open models (Gemma 4) |
| Genesis | Free | Robotics & Embodied AI | Unified multi-physics simulation engine plus photorealistic renderer for robotics/embodied-AI training, fully open source |
| Google AI Edge Gallery | Free | Local LLM Runners | Runs Gemma models fully on-device on Android and iOS, offline after one model download |
| GPT-OSS (OpenAI) | Free | Notable Open Models | OpenAI's Apache-2.0 open-weight reasoning models (120B and 20B) |
| GPT4All | Free | Local LLM Runners | Private local chat with your documents |
| IBM Granite | Free | Notable Open Models | Apache 2.0 licensed enterprise-grade model family |
| Jan | Free | Local LLM Runners | Open-source, offline ChatGPT alternative |
| Kimi K3 (Moonshot AI) | Free | Notable Open Models | Open-weight multimodal MoE with about 2.8T total and 104B active parameters, 1M-token context |
| KoboldCpp | Free | Local LLM Runners | Ships as a single portable executable with a bundled web UI (KoboldAI Lite) |
| LeRobot (Hugging Face) | Free | Robotics & Embodied AI | Open PyTorch library for training real-world robot control policies (ACT, Diffusion Policy, VLA models) |
| LitGPT | Free | Fine-Tuning & Training Frameworks | Clean from-scratch implementations of 20+ LLMs for pretraining, fine-tuning and deployment |
| Llama (Meta) | Free | Notable Open Models | Meta's flagship open-weight family (Llama 4) |
| llama.cpp | Free | Local LLM Runners | Pure C/C++ inference engine with minimal dependencies, runs on CPU-only hardware |
| llamafile | Free | Local LLM Runners | Packs model weights and runtime into one executable that runs on macOS, Windows and Linux |
| LM Studio | Free | Local LLM Runners | Polished desktop GUI for local models |
| LocalAI | Free | Local LLM Runners | Drop-in OpenAI-compatible API server running models on your own hardware, CPU or GPU |
| LongCat (Meituan) | Free | Notable Open Models | LongCat-2.0 open-weight 1.8T-parameter model with FP8 and INT8 builds |
| MediaPipe (Google AI Edge) | Free | Local LLM Runners | Cross-platform on-device ML for vision, audio, text and LLM inference |
| MLC LLM | Free | Local LLM Runners | Compiles and runs LLMs natively on iOS, Android, browsers (WebGPU), Mac, Windows and Linux |
| MLX-LM (Apple) | Free | Local LLM Runners | Purpose-built for Apple Silicon's unified memory architecture, faster than llama.cpp for many models on Mac |
| Moonshine | Free | Speech & Transcription Engines | Small streaming speech-recognition models for phones, browsers and low-power devices |
| ms-swift (ModelScope) | Free | Fine-Tuning & Training Frameworks | Fine-tuning and deployment framework supporting hundreds of LLMs and multimodal models |
| MuJoCo | Free | Robotics & Embodied AI | Fast, accurate physics engine for robotics and biomechanics research |
| Nemotron (NVIDIA) | Free | Notable Open Models | NVIDIA's open Nemotron 3 family of efficient agentic models |
| NVIDIA Isaac GR00T | Free | Robotics & Embodied AI | Open, Apache-2.0-licensed vision-language-action foundation model for generalist humanoid robots (GR00T N1.7) |
| NVIDIA Isaac Lab | Free | Robotics & Embodied AI | GPU-accelerated framework for robot reinforcement and imitation learning on Isaac Sim |
| Ollama | Free | Local LLM Runners | The default way to run LLMs locally |
| Open WebUI | Free | Local LLM Runners | Self-hosted ChatGPT-style interface |
| OpenAI Whisper | Free | Speech & Transcription Engines | Open-source speech-to-text, run locally free |
| OpenLLMetry (Traceloop) | Free | LLM Eval & Observability | OpenTelemetry-based instrumentation for LLM calls, vector DBs and frameworks |
| openpi (Physical Intelligence) | Free | Robotics & Embodied AI | Open-source weights and code for pi0, pi0-FAST and pi0.5 vision-language-action models |
| Phi (Microsoft) | Free | Notable Open Models | MIT-licensed small language models for on-device and edge use |
| Pleias | Free | Notable Open Models | Fully open-weight, open-dataset small language models (350M-3B) explicitly built for EU AI Act compliance |
| Sarvam Open Models (30B / 105B) | Free | Notable Open Models | Sarvam-105B and Sarvam-30B open models built for Indian languages, with FP8 and GGUF builds |
| SGLang | Free | Local LLM Runners | RadixAttention for automatic prefix-cache reuse across requests |
| TimesFM (Google Research) | Free | Notable Open Models | Pretrained decoder-only foundation model for time-series forecasting |
| TRL (Hugging Face) | Free | Fine-Tuning & Training Frameworks | Post-training library covering SFT, DPO, GRPO and reward modeling for open LLMs |
| Unsloth | Free | Fine-Tuning & Training Frameworks | Fine-tunes LLMs, diffusion, TTS and embedding models 2x faster with ~70% less VRAM than standard Hugging Face training |
| vLLM | Free | Local LLM Runners | PagedAttention memory management for high-throughput multi-request GPU serving |
| whisper.cpp | Free | Speech & Transcription Engines | C/C++ port of OpenAI Whisper running on CPU, Metal, Core ML, CUDA and Vulkan |
| WhisperX | Free | Speech & Transcription Engines | 70x real-time transcription speed via batched inference on top of Whisper |
| Artificial Analysis | Freemium | Leaderboards & Benchmarks | Independent cross-provider benchmarking of intelligence, speed and price for the same model across different hosting APIs |
| AssemblyAI | Freemium | Speech & Transcription Engines | Speech-to-text with audio intelligence |
| Baseten | Freemium | Model Hosting & Inference APIs | Basic plan is pay-as-you-go with free starter credits for new accounts |
| Braintrust | Freemium | LLM Eval & Observability | Free Starter plan ships model credits and scored evals with no card required |
| Cloudflare Workers AI | Freemium | Model Hosting & Inference APIs | 10,000 free 'Neurons' of inference per day on every account, resetting daily |
| Cohere Trial API | Freemium | Model Hosting & Inference APIs | Every account gets a free Trial API key covering chat, embed and rerank models |
| Deepgram | Freemium | Speech & Transcription Engines | Fast, accurate speech-to-text API |
| ElevenLabs Scribe | Freemium | Speech & Transcription Engines | Scribe v2 Realtime transcribes in under 150ms latency |
| Fireworks AI | Freemium | Model Hosting & Inference APIs | High-performance open-model serving |
| GLM (Z.ai) | Freemium | Notable Open Models | GLM-5.x flagship and Flash models released as open weights on Hugging Face |
| Google AI Studio | Freemium | Model Hosting & Inference APIs | Free-tier API access to Gemini Flash-family models with generous token allowances, no credit card required to start |
| Groq | Freemium | Model Hosting & Inference APIs | Ultra-fast inference on custom LPUs |
| Hugging Face | Freemium | Model Hosting & Inference APIs | The hub for open models and datasets |
| Langfuse | Freemium | LLM Eval & Observability | Fully open-source and self-hostable for free via Docker Compose/Kubernetes, not just a hosted SaaS |
| LangSmith | Freemium | LLM Eval & Observability | Tracing, evaluation datasets and prompt playground for LLM apps and agents |
| Mistral Voxtral | Freemium | Speech & Transcription Engines | Apache 2.0 open-weight models (24B and 3B) downloadable from Hugging Face |
| ModelScope | Freemium | Model Hosting & Inference APIs | Alibaba's open model hub with thousands of Qwen, Wan and community models |
| Novita AI | Freemium | Model Hosting & Inference APIs | Single API surface for 200+ LLM/image/video/audio models plus on-demand GPU and bare-metal instances |
| OpenRouter | Freemium | Model Hosting & Inference APIs | One API for 400+ models across providers |
| Opik (Comet) | Freemium | LLM Eval & Observability | Open-source LLM tracing, evaluation and prompt-optimization platform (Apache-2.0) |
| Promptfoo | Freemium | LLM Eval & Observability | Open-source CLI/library for evaluating prompts, models and RAG pipelines side by side, runs in CI |
| Soniox | Freemium | Speech & Transcription Engines | Real-time speech-to-text priced well under typical competitor rates |
| Speechmatics | Freemium | Speech & Transcription Engines | Free starting credit with no card required, 56+ language support |
| W&B Weave | Freemium | LLM Eval & Observability | Agent-native tracing model with sessions, steps, tools and sub-agents as first-class concepts (not generic spans) |
| Z.ai Open Platform (free GLM Flash API) | Freemium | Model Hosting & Inference APIs | GLM-4.7-Flash and GLM-4.5-Flash text models listed as free for input and output on the public API |
| Msty | Freemium | Local LLM Runners | Nexus module: unified gateway for managing model connections, credentials and usage policy across providers |
| NVIDIA Build | Freemium | Model Hosting & Inference APIs | Hosted catalog of 100+ open and NVIDIA models with an OpenAI-compatible endpoint |
| Cerebras Inference | Trial | Model Hosting & Inference APIs | Runs open models on Cerebras Wafer-Scale Engine hardware at dramatically higher tokens/sec than GPU-based APIs |
| Replicate | Trial | Model Hosting & Inference APIs | Run open models with one API call |
| DeepInfra | Paid | Model Hosting & Inference APIs | Very low per-token pricing across a large catalog of open models (text, image, audio) |
| Nebius Token Factory | Paid | Model Hosting & Inference APIs | European GPU-cloud-backed inference API hosting major open models (Llama, Qwen, DeepSeek, etc.) |
| SambaNova Cloud | Paid | Model Hosting & Inference APIs | Hosts open models (DeepSeek, MiniMax, Llama) on SambaNova's own RDU chips for high-speed inference |
| Together AI | Paid | Model Hosting & Inference APIs | Fast, cheap open-model inference |