asf0/Qwen3.8-27B-DFlash-GGUF
Text Generation • 2B • Updated • 968 • 1
ataide santos
asf0
AI & ML interests
Software engineering student. Local LLM inference, speculative decoding, and ROCm/HIP performance work.
Recent Activity
reacted to VictorSanh's post with 🔥 about 2 hours ago
We used weight space programming to bring Qwen 3.5 0.8B from 7.4% to 58.7% on Math 500.
Check out the weights!
https://huggingface.co/collections/rilixai/weight-space-programming-with-beaker
More details: https://www.withbeaker.ai/blog/weight-space-programming updated a model 17 days ago
asf0/Qwen3.8-27B-DFlash-GGUF updated a model 17 days ago
asf0/Qwen3.8-27B-DFlashOrganizations
None yet