Hysparse2 generates around 2560 bytes of KV cache per token while Deepseek V4.1 Flash is…
This is a AI post classified by Jev as AI infra & evals (a model release), kept by the AI Radar because it carries real work, not commentary.
Not bad Hysparse2 generates around 2560 bytes of KV cache per token while Deepseek V4.1 Flash is at 890 bytes per token It's still 2.8x worse than v4.1 Flash but much better than alternatives
Posted by Zephyr (172.9k followers) 1 h ago · 37 likes · 10k views · view the original post on X. Kept by the AI Radar as AI infra & evals.
More AI work like this
- 80+ companies. One ecosystem working to accelerate physical AI. — @Arm
- Comfy Router is live — @ComfyUI
- Tip: learn how to improve your AI model observability using Logs, Activity, and Broadcast. — @OpenRouter
- Can the rental price of GPUs predict stock prices? — @OrnnExchange
- What does it take to build a rackscale AI system? Our engineers bring AMD Helios to… — @AMD
- 🚀 Our DSpark for Qwen3.8-27B beats native MTP with the same 8 speculative tokens on… — @RedHat_AI
- Your model weights are encrypted at rest. Cool. — @CoreWeave
- We want to sponsor Rust maintainers and open-source projects across web development,… — @encoredotdev
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 44.5k posts from 5k X accounts over the last 14 days, 1.9k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 16:21 UTC. Full method.