We're sharing/showcasing best of @huggingface models. Follow to stay in loop. Promoting Open-Source models.
Joined December 2025
- Tweets31.7K
- Following32
- Followers71.8K
- Likes621
Hermes had the head start. Now a longtime Hermes user is testing Mercury, submitting 7 PRs, and asking for more.
Imagine what happens when Mercury is no longer the new kid on the block.
Hermes set the bar. Mercury is here to raise it.
Going through the testing with the new @mercury__agent and I am impressed. I have been straight up Hermes for a LONG time, wanted something new to test. Submitted 7 PR's on some bugs I found so far but honestly, this is impressive. Would love a desktop app but its barely born.
730 downloads and growing. Merged with mergekit for enhanced roleplay performance. GGUF format means easy deployment on consumer hardware. Dive into next-level character AI today.
31B parameters, based on Blazed-Forge/Gemma-4-Sphinsikus-Chronist-31B. Quantized to GGUF for efficient inference. Apache 2.0 licensed, so you can use it freely. English language focus.
Built for roleplay and storytelling. Run it locally with transformers or GGUF backends. Create rich characters, dynamic dialogues, and endless adventures. Perfect for interactive fiction and AI companions.
Meet Gemma-4-Sphinsikus-Chronist-31B-GGUF: a 31B roleplay powerhouse in GGUF format. Merged with mergekit and ready for your local setup. If you love immersive character AI, this one's for you.
With 292 downloads and a focus on uncensored creativity, this model stands out for roleplay and writing. The GGUF format ensures it runs on consumer hardware, giving you a private, unrestricted AI experience. Try it for your next creative project.
This is a 31B parameter model merged using mergekit, then converted to GGUF format for efficient inference. It's based on the Gemma architecture and tagged for transformers, making it compatible with popular tools. A solid choice for local deployment.
Use it for creative writing, immersive roleplay, or deep reasoning tasks. It handles both reasoning and non-reasoning modes, and since it's uncensored, it won't shy away from NSFW content. Build stories, characters, or explore ideas without filters.
Meet Gemma-4-Giftige-Blume-31B-v1-GGUF: a 31B merge model that's uncensored, creative, and ready for roleplay. It's a GGUF build, so you can run it locally with ease. Perfect for those who want a powerful, unrestricted AI companion.
With 1,592 downloads, it's gaining traction. The combination of MoE, long-context, and tool-calling in a GGUF package makes it a versatile pick for production and experimentation. Try it for your next AI project.
It's a mixture-of-experts model with bfloat16 weights, optimized for GGUF. Tags show long-context, reasoning, and tool-calling support. The i1-GGUF variant is quantized for speed, while BF16 keeps quality high. Great for vLLM and transformers.
Use it for chatbots that remember long chats, AI agents that call tools, or reasoning tasks. The MoE design keeps it efficient, and GGUF format means easy local deployment. Build smarter assistants without huge compute.
Meet KOLIBRI-1-DERISKED-BF16-i1-GGUF: a GGUF model built for long-context conversations, reasoning, and tool-calling. With MoE architecture and bfloat16 precision, it's ready for vLLM and transformers. Perfect for devs exploring efficient AI.
With 226 downloads and growing, this model offers solid reasoning performance in a compact package. Apache-2.0 license means you can use it commercially. Try it for your reasoning-heavy applications today!
Under the hood: phi3 architecture, quantized to GGUF for efficient inference. Trained with unsloth for speed, it supports English and integrates with transformers and text-generation-inference. Lightweight yet capable.