Alex Hant

hardhant

hardhant@gmail.com

AI & ML interests

None yet

Recent Activity

reacted to danielhanchen's post with 🔥 about 10 hours ago

Gemma 4 12B can now run locally on just 8GB RAM via Dynamic GGUFs. Google's new model, Gemma 4 12B Unified supports image, audio and 256K context. You can run and train the model via Unsloth Studio. GGUF: https://huggingface.co/unsloth/gemma-4-12b-it-GGUF Guide: https://unsloth.ai/docs/models/gemma-4

liked a model about 20 hours ago

Comfy-Org/Ideogram-4

reacted to ovi054's post with 🔥 about 24 hours ago

Qwen Image Edit 2511 Fast + LoRA ⚡ https://huggingface.co/spaces/ovi054/Qwen-Image-Edit-2511-LoRA QIE-2511 is an image editing model with integrated LoRA capabilities. You can add any custom LoRA to generate and edit images within this Space. 👉 Try it now: https://huggingface.co/spaces/ovi054/Qwen-Image-Edit-2511-LoRA

View all activity

Organizations

None yet

reacted to danielhanchen's post with 🔥 about 10 hours ago

Post

2056

Gemma 4 12B can now run locally on just 8GB RAM via Dynamic GGUFs.

Google's new model, Gemma 4 12B Unified supports image, audio and 256K context.
You can run and train the model via Unsloth Studio.

GGUF: unsloth/gemma-4-12b-it-GGUF
Guide: https://unsloth.ai/docs/models/gemma-4

liked a model about 20 hours ago

Comfy-Org/Ideogram-4

Updated 1 day ago • 42

reacted to ovi054's post with 🔥 about 24 hours ago

Post

2494

Qwen Image Edit 2511 Fast + LoRA ⚡

ovi054/Qwen-Image-Edit-2511-LoRA

QIE-2511 is an image editing model with integrated LoRA capabilities. You can add any custom LoRA to generate and edit images within this Space.

👉 Try it now: ovi054/Qwen-Image-Edit-2511-LoRA

liked 4 models 1 day ago

liked 2 models 2 days ago

JetBrains/Mellum2-12B-A2.5B-Thinking

Text Generation • 12B • Updated 3 days ago • 12.2k • 203

Comfy-Org/PixelDiT

Updated 2 days ago • 55.3k • 74

reacted to FlameF0X's post with 🔥 3 days ago

Post

6875

MiniMax-M3 coming soon.
https://github.com/MiniMax-AI/MiniMax-M3

liked 3 models 3 days ago

nvidia/Cosmos3-Super

65B • Updated 4 days ago • 16.8k • 134

ACE-Step/acestep-v15-xl-turbo-diffusers

Text-to-Audio • Updated May 1 • 2.31k • 18

ACE-Step/acestep-v15-xl-sft-diffusers

Text-to-Audio • Updated 2 days ago • 80 • 3

liked 3 models 4 days ago

nvidia/Cosmos3-Super-Text2Image

Text-to-Image • 65B • Updated 4 days ago • 961 • 108

mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF

36B • Updated 14 days ago • 44.3k • 44

mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-GGUF

35B • Updated Apr 27 • 33.3k • 74

liked a model 5 days ago

sanyixiansheng/hunyuanimage-gguf

Text-to-Image • 17B • Updated Mar 31 • 510 • 2

reacted to prithivMLmods's post with 🔥 7 days ago

Post

6087

PiD — Pixel Diffusion Decoder Image Edit Upscale and Image Generation Upscale, an all-in-one demo, is now live on Spaces! Great improvements in realism-based image generation and editing are powered by FLUX.2-Klein, while image generation is paired with Z-Image, and upscaling is enabled by default!

🤗 Space: prithivMLmods/PiD-Image-Upscaler
🔗 Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection

🤗 > To learn more, visit the app page or the respective model pages.

reacted to SeaWolf-AI's post with 🔥 7 days ago

Post

4201

Darwin-60B-DUO: Two SOTAs, One Endpoint — 88.38% on GPQA Diamond 🚀

We're excited to release Darwin-60B-DUO, the Darwin family's first DUO model. Take two domain-verified specialists, hide them behind a single OpenAI-compatible endpoint, and let a router decide which one (or both) answers. You see one model, one API — but get the best of both.

The number that matters: on the full 198-question GPQA Diamond, Darwin-60B-DUO hits 88.38%. The constituents alone land at 69.70% (Darwin-28B-REASON) and 77.27% (AWAXIS-Think-31B); a naive cascade only reaches 83.84%. The DUO clears them all. Two small specialists, intelligently routed, beat one big generalist on cost and quality. Both are independently verified — Darwin-28B-REASON is #3 on the HF GPQA Diamond leaderboard, AWAXIS-Think-31B is #1 on Korea's national K-AI Leaderboard (MSIT).

The brains is a Hybrid-A router picking one of five strategies on the fly. Korean → AWAXIS, English/STEM → Darwin (single-backend, ~70% of traffic at 1× cost). When a Korean answer needs rigorous English reasoning, split_refine fires — Darwin drafts, AWAXIS polishes; MCQ/short-answer runs both with self-consistency + cross-verify. Net effective cost: only ~1.3× a single 30B model.

The part the community will care about: the gateway is model-agnostic and Apache-2.0. Point it at any two OpenAI-compatible backends and you've got a DUO in minutes — teach router.py when to use which, and parallel calls, response merging, and routing transparency via _duo_route are handled for you. Fork it and tell us what you built.

Painless deploy: docker compose up for both vLLM backends + gateway; FP8 ~30GB colocates on a single B200/H100. One git clone (~120GB). Text-only for now, streaming in v1.1.
Two SOTAs, one endpoint. Come build your own on the Community tab.

👇
🔗 FINAL-Bench/Darwin-60B-DUO

liked a model 8 days ago

Qwen/Qwen-Image-Bench

Image-Text-to-Text • 27B • Updated 8 days ago • 7.31k • 50

Alex Hant

AI & ML interests

Recent Activity

Organizations

hardhant's activity