Hugging Face's logo
Jonna Matthiesen's picture
11 4 12

Jonna Matthiesen

JonnaMat
embedl
salomons's profile picture ginigen-ai's profile picture VladRva's profile picture
Ā·

AI & ML interests

None yet

Recent Activity

updated a Space 1 day ago
embedl/Edge-Inference-Benchmarks
liked a model 7 days ago
embedl/Cosmos-Reason2-2B-W4A16-Edge2-FlashHead
posted an update 7 days ago
āš” FlashHead benchmarks for Llama 3.2, Gemma 3, and Qwen3 are now on https://huggingface.co/spaces/embedl/Edge-Inference-Benchmarks ! These are some of the models used in the FlashHead paper - now easier to explore and compare interactively. šŸš€ Jetson AGX Thor (tok/s, batch=1): - Llama-3.2-1B: 77 ā†’ 285 (FlashHead+W4A16, 3.7x) - Llama-3.2-3B: 34 ā†’ 112 (3.3x) - Gemma-3-1B: 79 ā†’ 153 (1.9x) - Qwen3-1.7B: 49 ā†’ 189 (3.8x) - Qwen3-0.6B: 140 ā†’ 177 (1.3x) āœ… Accuracy matches baseline on MMLU-Pro, IFEval, BBH, TruthfulQA, GSM8K.
View all activity

Organizations

Embedl's profile picture