We're sharing/showcasing best of @huggingface models. Follow to stay in loop. Promoting Open-Source models.

Joined December 2025
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.
1
44
8,942
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.
1
422
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.
1
84
Meet phi4-reasoning-supervisor-v1: a GGUF model fine-tuned for reasoning tasks. Built on phi3 architecture, it's ready for text-generation-inference and comes with an Apache-2.0 license. Perfect for your next reasoning project!
1
598
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!
1
181
Meet Alternate-Qwen3.5-9B-Claude-4.6-Opus-GGUF: a 9B conversational model that blends Qwen3.5 with Claude 4.6 Opus vibes. GGUF format means it runs locally on your machine, no cloud needed. Perfect for chat apps and experiments.
2
2
726
With 193 downloads and growing, this model proves that small, local models can deliver big conversational quality. It's endpoints compatible, meaning easy integration with your existing tools. Give it a try and see the difference.
1
199
Meet Qwopus3.5-9B-v3-GGUF: a 9B model built for reasoning and competitive programming. With chain-of-thought and LoRA fine-tuning, it's a lean mean coding machine you can run locally. #AI #LLM
3
4
820
With 317 downloads and growing, this model proves small can be mighty. It delivers chain-of-thought reasoning and competitive programming skills in a compact package. Perfect for developers who want power without the bulk.
1
224