Hannes von Essen

HannesVonEssen

1 1 24

https://hfviewer.com/

AI & ML interests

Deep Learning Researcher at Embedl | Creator of hfviewer.com

Recent Activity

liked a model 3 days ago

IvmeLabs/Ivme-Conversate-v2-Base

liked a model 3 days ago

Quazim0t0/Chimera-64M

repliedto their post 5 days ago

📣 Understand any Hugging Face model! 💬 You can now hover a node to get a nice animated explanation of how the operation works and which paper introduced it! https://hfviewer.com 🎞️ Also, embedded HF Viewer graphs now default to being animated! Create and customize your animation at https://hfviewer.com/model-card-embed 👥 Finally, feel free to join our discord to influence the future direction of HF Viewer! https://discord.gg/a5eEmtTTPV

View all activity

Organizations

replied to their post 5 days ago

Thanks for the report, this is now fixed! :)

posted an update 6 days ago

Post

1187

📣 Countdown Kimi K3 with us!

Read our deep dive into the architecture of Kimi K3 and get notified on July 27 when it gets released and is viewable on hfviewer.com!

https://hfviewer.com/moonshotai/kimi-k3

posted an update 10 days ago

Post

109

📣 Understand any Hugging Face model!

💬 You can now hover a node to get a nice animated explanation of how the operation works and which paper introduced it! https://hfviewer.com

🎞️ Also, embedded HF Viewer graphs now default to being animated! Create and customize your animation at
https://hfviewer.com/model-card-embed

👥 Finally, feel free to join our discord to influence the future direction of HF Viewer! https://discord.gg/a5eEmtTTPV

2 replies

posted an update 18 days ago

Post

156

📣 HF Viewer now supports Hugging Face login! 🤗

⚡ Generate visualizations for all your models at once!

😎 Feature your models in the community showcase and set up your own profile/org collection page on hfviewer!

✍️ Write your own model articles on hfviewer in the same novel interactive style as our "Gemma 4 family" article - with linking between the graph nodes and article text!

📊 We are also now rolling out support for tensor shapes, FLOPs and param counts per layer! :)

Thanks for all your positive feedback and suggestions! ❤️

Try the logged in experience here: https://hfviewer.com/

Here are some really cool articles already written by our users:

📑 LFM2.5-Audio: edge-first speech inference by Anna Piunova at Liquid AI
https://hfviewer.com/LiquidAI/LFM2.5-Audio-1.5B

📑 DeepSeek V4 mHC Explained by Shakti Wadekar
https://hfviewer.com/deepseek-ai/DeepSeek-V4-Pro

📑 Borealis - open recipe for training Audio LLMs by Alex Wortega
https://hfviewer.com/Vikhrmodels/Borealis-5b-it

1 reply

posted an update 2 months ago

Post

4932

📣 Add architecture visualization to model card!

🌟 For all creators out there: add a model visualization to your model card to capture your audience's attention!

🖱️ When clicked, it opens an interactive view with multiple levels of granularity!

1️⃣ Paste url at https://hfviewer.com/model-card-embed
2️⃣ Paste generated code in your README.md!
3️⃣ ✨

replied to their post 3 months ago

Hi! Simply paste the link to the Hugging Face model you want to view on https://hfviewer.com, or install the extension from the post to have it automatically on all model pages you visit! :)

posted an update 3 months ago

Post

11674

📣 Hugging Face Visualizer, now as Chrome extension!
https://hfviewer.com

✨ After installing, Hugging Face model pages will have an architecture visualization on the model page itself!

🔗 Link:
https://chromewebstore.google.com/detail/hugging-face-viewer/mmadlggmpkpiockpjfepaohcllbnakej

Thanks for all the nice feedback so far! ❤️

5 replies

reacted to unmodeled-tyler's post with 😎 3 months ago

Post

4130

Hey Hugging Face!

Repo: https://github.com/unmodeled-tyler/vessel-browser

I wanted to share a cool feature from my open source AI native web browser, Vessel: Persistent highlights!

You can highlight anything on the page and the context is provided to the agent. It's kind of a fun way to learn about new stuff, synthesize info, or just deepen your comprehension/understanding.

Since highlights are persistent, you can close the page, come back later - and your highlights will be exactly where you left them. I've found this particularly useful when reviewing technical blogs, model cards, etc.

Check it out!

1 reply

posted an update 3 months ago

Post

276

📣 I made a visualizer for Hugging Face models: https://hfviewer.com

✨ Simply paste a Hugging Face URL to get an interactive visualization of the architecture!

🔗 The recent Qwen3.6-27B model as an example: https://hfviewer.com/Qwen/Qwen3.6-27B

Feel free to try it out and give me feedback on how it can be improved! ❤️

1 reply

reacted to JonnaMat's post with 🔥🚀 5 months ago

Post

1090

Qwen3.5 on-device benchmarks on the Nvidia Jetson lineup are now live 🚀

We've added the latest Qwen3.5 models (0
8B - 9B) to our on-device inference benchmarks (Nvidia Jetson Orin Nano Super, AGX Orin, AGX Thor).

👉 Explore TPS, TTFT, E2E latency, and TPOT. Measured on real hardware: embedl/Edge-Inference-Benchmarks

🌟 Stay tuned for additional benchmarks and Embedl-optimized models: Enabling models run faster and on less expensive hardware.

If you're working on edge LLM deployment, we'd love to discuss your use case.

1 reply

reacted to JonnaMat's post with 🔥 5 months ago

Post

1620

🤯 Edge-Grade Vision Reasoning. Now Practically Lossless. 🤯

Introducing
👉 embedl/Cosmos-Reason2-2B-W4A16-Edge2
Optimized for Jetson Orin Nano Super and AGX Orin

nvidia .

🚄 Try it out on Jetson (image+video+text):

docker run --rm -it \
  --network host \
  --shm-size=8g \
  --ulimit memlock=-1 \
  --ulimit stack=67108864 \
  --runtime=nvidia \
  --name=vllm-serve \
  -e HF_TOKEN=hf_*** \
  -e HF_HOME=/root/.cache/huggingface \
  ghcr.io/nvidia-ai-iot/vllm:latest-jetson-orin \
  vllm serve "embedl/Cosmos-Reason2-2B-W4A16-Edge2" \
    --max-model-len 8192 \
    --gpu-memory-utilization 0.75 \
    --max-num-seqs 2

🤓 What is Edge2? Most weights → INT4 | Activations → FP16 | Select sensitive layers → kept in FP16.
Edge2 preserves precision where it matters most; while keeping the model small and fast enough for edge GPUs. 😎

posted an update 5 months ago

Post

1373

Cosmos-Reason2-2B on Nano Super

Hi! Today, me and my team is releasing a version of Cosmos-Reason2-2B that is quantized so that it fits on the NVIDIA Jetson Orin Nano Super.

We managed to find a mixed precision configuration such that it maintains virtually the same accuracy as the unquantized model while being able to run really efficiently on the Nano Super and other edge devices :)

embedl/Cosmos-Reason2-2B-W4A16-Edge2

reacted to JonnaMat's post with 🔥 5 months ago

Post

2569

⚡ Blackwell-native Vision Reasoning at the edge ⚡

Released a NVFP4A16-variant of nvidia/Cosmos-Reason2-2B:
embedl/Cosmos-Reason2-2B-NVFP4A16

💖 Optimized for Blackwell with minimal accuracy drop compared to its FP16 counterpart.

Thorough on-device benchmarks on AGX Thor in the modelcard. 🤓 📊

Try it out:

docker run --rm -it \
  --network host \
  --shm-size=8g \
  --ulimit memlock=-1 \
  --ulimit stack=67108864 \
  --runtime=nvidia \
  --name=vllm-serve \
  -e HF_TOKEN=hf_*** \
  -e HF_HOME=/root/.cache/huggingface \
  nvcr.io/nvidia/vllm:26.01-py3 \
  vllm serve "embedl/Cosmos-Reason2-2B-NVFP4A16" \
    --host 0.0.0.0 \
    --port 8000 \
    --tensor-parallel-size 1 \
    --max-model-len 16384 \
    --gpu-memory-utilization 0.9

Hannes von Essen

AI & ML interests

Recent Activity

Organizations

HannesVonEssen's activity