Bitfield
Summary
Bitfield is a database claiming to be the fastest in the world with read speeds of 0.69ns and write speeds of 0.58ns.
Similar Articles
Spent two weeks on a kernel that benchmarked 29x faster. End to end it's maybe 6-10%, and it's not even wired in yet.
The author optimized a matmul kernel for BitNet's ternary models on CPU, achieving 29x speedup in isolation, but found that the model is memory-bound, resulting in only 6-10% end-to-end gain. The inference engine is available as open-source.
Built a from-scratch BitNet inference engine in pure C — 1.8× faster than bitnet.cpp on Xeon (36 tok/s), zero dependencies [BitNet & Bonsai CPU testers wanted]
Project Zero is a from-scratch C99 LLM inference engine that runs BitNet and Qwen Bonsai-27B on CPU with zero dependencies, achieving 1.8× speedup over bitnet.cpp on Xeon. The project seeks community benchmarks for both models.
@witcheer: everyone says NVFP4 makes blackwell cards "faster." I benchmarked Qwen3.6-27B three ways on my 5090: >NVFP4 >plain Q4_K…
A benchmark of NVFP4 on an RTX 5090 with Qwen3.6-27B shows prefill speed gains of 32-42% over equal-bit Q4_K_M and 52-68% over Q6_K, but decode gains are modest (+9% vs Q4) as decode is memory-bandwidth bound. The quality loss compared to Q6 is minimal (-0.8 average), making NVFP4 a good choice for local inference.
China’s DFSX Offers 2x The Memory Bandwidth Of NVIDIA’s GB200
China's DFSX claims its TY64 SuperNode, built with 14nm DF2000 chips using a 3.5D Infinity Chiplet layout, offers 960TB/s memory bandwidth—2x that of NVIDIA's GB200 NVL72—though with lower raw compute (64 PFLOPS BF16 vs 360 PFLOPS).
Bitnet.cpp: Efficient Edge Inference for Ternary LLMs
Bitnet.cpp presents a mixed-precision matrix multiplication library for efficient edge inference of ternary LLMs like BitNet b1.58, achieving up to 6.25x speedup over full-precision baselines. The system is open-sourced on GitHub.