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
@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.
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.
5x perf increase on writes with FPW disabled in Postgres
This article explains how Databricks' Lakebase architecture achieves a 5x improvement in Postgres write throughput by disabling Full Page Writes (FPW) and leveraging stateless compute with distributed storage.
Removing fsync from our local storage engine
FractalBits introduces a specialized single-node KV storage engine that eliminates fsync calls to achieve significantly higher write throughput on NVMe SSDs by managing durability directly at the hardware level.
Benchmarking Self-Hosted Gemma 2 9B vs. Frontier APIs: The FP8 Quantization Prefill Tax and VRAM Realities on an NVIDIA L4 [P]
This benchmark compares an unquantized Gemma 2 9B model with an FP8 quantized variant on an NVIDIA L4 GPU, revealing that FP8 quantization introduces a prefill tax (higher TTFT) but improves decoding latency and VRAM usage, with minimal semantic drift for narrow tasks.