# The best free ai models & local execution tools

All 109 ai models & local execution tools in the catalog across 8 sub-categories, ordered free tiers first.

## Stats

- 109 tools listed
- 103 free or freemium
- 76 with no paid plan at all
- 8 sub-categories covered

## FAQ

### What are the best free ai models & local execution tools?

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.

### Which of these are completely free?

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.

### How is this list ordered?

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.

## Quick picks

### Which AI Models & Local Execution Tools work in a browser with no install?

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.

### Which AI Models & Local Execution Tools let you sign in with Google?

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.

### Which AI Models & Local Execution Tools have a mobile app?

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.

### Which AI Models & Local Execution Tools can you self-host or run offline?

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.

## Tools

- [Arize Phoenix](https://aitools.flocci.in/tool/arize-phoenix) — Free — Fully open-source, self-hostable with zero setup via `uvx` (pip/conda also supported)
- [DeepSeek Models](https://aitools.flocci.in/tool/deepseek-models) — Free — DeepSeek V4-Pro and V4-Flash open-weight MoE models, MIT-licensed
- [Design Arena](https://aitools.flocci.in/tool/design-arena) — Free — Crowdsourced Bradley-Terry (Elo-style) ranking of AI models specifically on design/aesthetic quality, not raw capability
- [Epoch AI](https://aitools.flocci.in/tool/epoch-ai) — Free — Independent, non-vendor research institute tracking AI compute, training cost and capability trends over time
- [ERNIE 4.5 Open Models (Baidu)](https://aitools.flocci.in/tool/ernie-4-5-open-models-baidu) — Free — ERNIE-4.5 family including 21B-A3B Thinking and VL-424B-A47B multimodal MoE
- [Falcon (TII)](https://aitools.flocci.in/tool/falcon-tii) — Free — Falcon-H1 hybrid Transformer-Mamba family for efficient long-context inference
- [Google Stax](https://aitools.flocci.in/tool/google-stax) — Free — Build evals with human raters or LLM autoraters on your own data
- [Hunyuan (Tencent)](https://aitools.flocci.in/tool/hunyuan-tencent) — Free — Open-weight Hunyuan Hy3 and Hy4-preview flagship text models
- [Laminar](https://aitools.flocci.in/tool/laminar) — Free — Open-source observability and evals platform for AI agents (Apache-2.0)
- [LiveBench](https://aitools.flocci.in/tool/livebench) — Free — Continuously refreshed questions to avoid benchmark contamination
- [LLaMA-Factory](https://aitools.flocci.in/tool/llama-factory) — Free — Zero-code Web UI (LLaMA Board) for fine-tuning 100+ open models without writing training scripts
- [LMArena (Arena.ai)](https://aitools.flocci.in/tool/lmarena-arena-ai) — Free — Crowd-voted 'Battle Mode' blind head-to-head comparisons across text, image, and coding/agent models
- [MiniMax M2 (open weights)](https://aitools.flocci.in/tool/minimax-m2-open-weights) — Free — 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)](https://aitools.flocci.in/tool/mistral-open-models-magistral-devstral-voxtral) — Free — Open-weight Mistral Medium 3.5, Small 4 and Large 3 general models
- [NVIDIA Canary-Qwen 2.5B](https://aitools.flocci.in/tool/nvidia-canary-qwen-2-5b) — Free — Speech-recognition plus LLM hybrid model that transcribes and can summarize or answer questions about audio
- [NVIDIA Cosmos](https://aitools.flocci.in/tool/nvidia-cosmos) — Free — Open platform of world foundation models, datasets and tools for physical AI
- [NVIDIA Parakeet](https://aitools.flocci.in/tool/nvidia-parakeet) — Free — Tops the Hugging Face Open ASR Leaderboard with 6.05% average WER at 0.6B params
- [OLMo (Ai2)](https://aitools.flocci.in/tool/olmo-ai2) — Free — Only major model family shipping full pretraining data (Dolma), code and intermediate checkpoints, not just weights
- [Open ASR Leaderboard (Hugging Face)](https://aitools.flocci.in/tool/open-asr-leaderboard-hugging-face) — Free — Ranks speech-recognition models by word error rate and real-time speed across English and multilingual sets
- [Qwen (Alibaba)](https://aitools.flocci.in/tool/qwen-alibaba) — Free — Open Qwen3.x family from phone-sized to multi-trillion-parameter MoE, Apache 2.0
- [Seed-OSS (ByteDance)](https://aitools.flocci.in/tool/seed-oss-bytedance) — Free — Seed-OSS-36B open reasoning LLM with native 512K-token context, Apache 2.0
- [sherpa-onnx](https://aitools.flocci.in/tool/sherpa-onnx) — Free — Offline speech-to-text, text-to-speech, VAD and speaker diarization without internet
- [Step (StepFun)](https://aitools.flocci.in/tool/step-stepfun) — Free — Step-3.7-Flash open multimodal model with FP8, NVFP4 and GGUF builds
- [SWE-bench](https://aitools.flocci.in/tool/swe-bench) — Free — The standard benchmark for evaluating autonomous coding agents on real GitHub issue resolution
- [Xiaomi MiMo](https://aitools.flocci.in/tool/xiaomi-mimo) — Free — MiMo-V2.6-Pro (1T parameters) and V2.6-Flash (311B) open-weight reasoning and agent models
- [AI Toolkit (Ostris)](https://aitools.flocci.in/tool/ai-toolkit-ostris) — Free — All-in-one trainer for LoRAs on diffusion and video models (FLUX, Wan and more)
- [AnythingLLM](https://aitools.flocci.in/tool/anythingllm) — Free — All-in-one local RAG and agents app
- [Axolotl](https://aitools.flocci.in/tool/axolotl) — Free — Config-file-driven fine-tuning workflow (YAML) covering LoRA, QLoRA, full fine-tuning, preference tuning and RL
- [BitNet](https://aitools.flocci.in/tool/bitnet) — Free — Official inference framework for 1-bit (ternary) LLMs
- [DeepEval](https://aitools.flocci.in/tool/deepeval) — Free — Open-source LLM evaluation framework with pytest-style tests and 50+ metrics
- [EleutherAI LM Evaluation Harness](https://aitools.flocci.in/tool/eleutherai-lm-evaluation-harness) — Free — Standard open framework for running hundreds of benchmarks (MMLU, GSM8K and more) against any LLM
- [EXAONE (LG AI Research)](https://aitools.flocci.in/tool/exaone-lg-ai-research) — Free — EXAONE 4.5: LG's first open-weight vision-language model for industrial use cases
- [exo](https://aitools.flocci.in/tool/exo) — Free — Links everyday devices (Macs, PCs, phones) into one cluster to run models too large for a single machine
- [faster-whisper](https://aitools.flocci.in/tool/faster-whisper) — Free — Whisper reimplementation on CTranslate2, up to 4x faster with less memory
- [FunASR](https://aitools.flocci.in/tool/funasr) — Free — Open-source speech recognition toolkit with Paraformer and SenseVoice models
- [Gemma (Google)](https://aitools.flocci.in/tool/gemma-google) — Free — Google's lightweight open models (Gemma 4)
- [Genesis](https://aitools.flocci.in/tool/genesis) — Free — Unified multi-physics simulation engine plus photorealistic renderer for robotics/embodied-AI training, fully open source
- [Google AI Edge Gallery](https://aitools.flocci.in/tool/google-ai-edge-gallery) — Free — Runs Gemma models fully on-device on Android and iOS, offline after one model download
- [GPT-OSS (OpenAI)](https://aitools.flocci.in/tool/gpt-oss-openai) — Free — OpenAI's Apache-2.0 open-weight reasoning models (120B and 20B)
- [GPT4All](https://aitools.flocci.in/tool/gpt4all) — Free — Private local chat with your documents
- [IBM Granite](https://aitools.flocci.in/tool/ibm-granite) — Free — Apache 2.0 licensed enterprise-grade model family
- [Jan](https://aitools.flocci.in/tool/jan) — Free — Open-source, offline ChatGPT alternative
- [Kimi K3 (Moonshot AI)](https://aitools.flocci.in/tool/kimi-k3-moonshot-ai) — Free — Open-weight multimodal MoE with about 2.8T total and 104B active parameters, 1M-token context
- [KoboldCpp](https://aitools.flocci.in/tool/koboldcpp) — Free — Ships as a single portable executable with a bundled web UI (KoboldAI Lite)
- [LeRobot (Hugging Face)](https://aitools.flocci.in/tool/lerobot-hugging-face) — Free — Open PyTorch library for training real-world robot control policies (ACT, Diffusion Policy, VLA models)
- [LitGPT](https://aitools.flocci.in/tool/litgpt) — Free — Clean from-scratch implementations of 20+ LLMs for pretraining, fine-tuning and deployment
- [Llama (Meta)](https://aitools.flocci.in/tool/llama-meta) — Free — Meta's flagship open-weight family (Llama 4)
- [llama.cpp](https://aitools.flocci.in/tool/llama-cpp) — Free — Pure C/C++ inference engine with minimal dependencies, runs on CPU-only hardware
- [llamafile](https://aitools.flocci.in/tool/llamafile) — Free — Packs model weights and runtime into one executable that runs on macOS, Windows and Linux
- [LM Studio](https://aitools.flocci.in/tool/lm-studio) — Free — Polished desktop GUI for local models
- ... and 59 more — see the full list on the page.
---

Source: Flocci AI Tools — https://aitools.flocci.in/best/best-ai-models-local-execution-tools

Facts last verified: October 2026