Community challenge pits MLX vs CUDA to speed up local Qwen 3.8 Flash on DGX Spark
gajesh · x · 2026-09-11
A community platform launched Qwen 3.8-Flash-Next with its first local-inference speed challenge, running the same model on two stacks with progress charted on one graph: a CUDA track using antirez's ds4 C/CUDA engine with Unsloth's GGUF quant on a single NVIDIA DGX Spark, and a Swift/Metal MLX track. "Let the optimizations begin."
Related event: Qwen 3.8 Flash Next Optimization Challenge: MLX and CUDA Both Gain Over 55%(2 posts)→
More from coding & agent
- Rethinking dependencies in the agent era: drop libs that save 20 lines of code — gethackteam · 2026-10-26
- RustGIS hits 2,000 GitHub stars in two weeks with agent-first architecture — giswqs · 2026-10-26
- Vercel Ships 12 New Products at Its 2026 Conference as It Races Rivals for the Agent Entry Point — FinanceYF5 · 2026-10-26
- Build an AI agent from scratch in under 50 lines of pure Python: ReAct loop tutorial — adnan_hashmi · 2026-10-26
- Dense instance segmentation via Muse Wonder + SAM 3.1 on Meta's Model API — nikhilaravi · 2026-10-26
- Security tip: use AI agents to build a NIST CSF knowledge base for incident response — prasanna_says · 2026-10-26