gemma-4-E4B-it
Productivityany to any model by google on Hugging Face (transformers). 4,208,952 downloads in the last 30 days as of 2026-10-15.
Free
LFM3-Omni-2B-MLX-bf16
any to any model by LiquidAI on Hugging Face (mlx). 1,044 downloads in the last 30 days as of 2026-10-15.
What is LFM3-Omni-2B-MLX-bf16?
LFM3-Omni-2B-MLX-bf16 is an open AI model published on Hugging Face by LiquidAI for any-to-any multimodal. Its name indicates a size of about 2B parameters, packaged as weights converted for Apple's MLX framework (Apple-silicon Macs). Hugging Face reported 1,044 downloads in the 30 days to 2026-10-15. Weights are free to download from Hugging Face; licence terms are set by the publisher on the model card.
| Publisher | LiquidAI |
|---|---|
| Task | any-to-any multimodal |
| Parameters (from name) | 2B |
| Format | MLX |
| Library | mlx |
| Downloads (30 days) | 1,044 (as of 2026-10-15) |
| Price | Free to download (open weights) |
LFM3-Omni-2B-MLX-bf16 pricing
Listed as Free. Detailed prices haven't been checked from the official site yet; see LFM3-Omni-2B-MLX-bf16.
How to run LFM3-Omni-2B-MLX-bf16
- Use an Apple-silicon Mac and install `mlx-lm` (pip install mlx-lm).
- Load it with mlx_lm using the repo id LiquidAI/LFM3-Omni-2B-MLX-bf16.
- Check the model card for the prompt format and licence.
Models related to LFM3-Omni-2B-MLX-bf16
gemma-4-E2B-it
Productivityany to any model by google on Hugging Face (transformers). 3,215,531 downloads in the last 30 days as of 2026-10-15.
Free
gemma-4-12B-it
Productivityany to any model by google on Hugging Face (transformers). 1,642,594 downloads in the last 30 days as of 2026-10-15.
Free
gemma-4-E4B-it-MLX-4bit
Productivityany to any model by lmstudio-community on Hugging Face (transformers). 1,126,659 downloads in the last 30 days as of 2026-10-15.
Free
gemma-4-E4B-it-MLX-8bit
Productivityany to any model by lmstudio-community on Hugging Face (transformers). 1,097,144 downloads in the last 30 days as of 2026-10-15.
Free
gemma-4-E4B-it-MLX-6bit
Productivityany to any model by lmstudio-community on Hugging Face (transformers). 1,089,186 downloads in the last 30 days as of 2026-10-15.
Free
LFM3-Omni-2B-MLX-bf16 FAQ
What is LFM3-Omni-2B-MLX-bf16?
LFM3-Omni-2B-MLX-bf16 is an open AI model published on Hugging Face by LiquidAI for any-to-any multimodal. Its name indicates a size of about 2B parameters, packaged as weights converted for Apple's MLX framework (Apple-silicon Macs).
Is LFM3-Omni-2B-MLX-bf16 free?
LFM3-Omni-2B-MLX-bf16 is listed as free.
How do I use LFM3-Omni-2B-MLX-bf16?
1. Use an Apple-silicon Mac and install `mlx-lm` (pip install mlx-lm). 2. Load it with mlx_lm using the repo id LiquidAI/LFM3-Omni-2B-MLX-bf16. 3. Check the model card for the prompt format and licence.
What models are similar to LFM3-Omni-2B-MLX-bf16?
Related models include gemma-4-E4B-it, gemma-4-E2B-it, gemma-4-12B-it, gemma-4-E4B-it-MLX-4bit, gemma-4-E4B-it-MLX-8bit.
This page is generated from public listing data (source listing, tags, counts and our own link check); check the official page for features, licence and current pricing. Want to master tools like this? See the 100+ AI Tools Course.