FlashML-org/FreeVideo
Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.
Local video generation from MiniMax H3, built to fit modest GPUs — FreeVideo packages MiniMax H3 video generation (via Video DeltaNet acceleration) to run on consumer hardware, as little as 8GB VRAM and 16GB RAM. Recent releases add H3 image generation up to 16MP, minute-long video output, a timeline editing view, and AI agent integration (Claude Code, Codex) for autonomous video creation. Ships as native desktop apps for Windows, macOS and Linux.
Metrics
Retention can be computed 30 days after a repository first trends (it isn't shown until then). See About for how each metric is defined.
Star growth and Trending appearances (last 30 days)
Bands mark days on the trending list (darker = higher rank)
Daily trending ranks as a table (1 days)
| Date | Daily |
|---|---|
| Nov 20, 2026 | python #16 +118 |
Created Sep 14, 2026 · First on trending Nov 20, 2026
Other notable repositories in the same category (LLMs & ML)
- hyperionaidev/smolmaxxing
- huawei-csl/MACaQ
- yuu551/amazon-bedrock-practical-guide-samples
- hatchet-dev/distributed-ray-tracer
- AInVFX/ainvfx-paintaplate
See all LLMs & ML repositories →
Rank within inference
| # | Repository | ★ |
|---|---|---|
| 1 | vllm-project/vllm | 97,238 |
| 2 | sgl-project/sglang | 38,863 |
| 3 | SYSTRAN/faster-whisper | 26,879 |
| 4 | FlashML-org/FreeToken | 17,322 |
| 5 | openvinotoolkit/openvino | 11,595 |
| 6 | vllm-project/semantic-router | 6,511 |
| 7 | FlashML-org/FreeVideo | 3,482 |
| 8 | trymirai/uzu | 3,372 |
| 9 | vllm-project/vllm-ascend | 3,122 |
| 10 | theagentrouter/agent-router | 2,422 |