EdgeRock-4B holds KV cache at 72 MiB across 256K context, 99.1% smaller than Qwen3.5-4B
alifcoder · x · 2026-10-27
EdgeRock's architecture keeps attention KV cache at a fixed 72 MiB per sequence at 256K context — 99.1% smaller than Qwen3.5-4B's 8 GiB. Fixed-capacity Rock Memory Anchors (RMA) store learned memories as directly readable KV records in a fixed-size bank, retrievable even after information leaves the local attention window, combining recurrent state and local attention for longer reasoning tasks.
Related event: EdgeRock Open-Sources Model with Constant 72 MiB KV Cache at 256K Context(2 posts)→
More from Infra
- YC-backed Hopper launches voice-agent inference cloud: 80 ms TTFT at $0.30/1M tokens — ycombinator · 2026-10-27
- A100 rental prices still rising in 2026 per a16z data, Jevons paradox hits compute — VraserX · 2026-10-27
- Anthropic S-1 reveals $800B+ in off-books future compute commitments — GaryMarcus · 2026-10-27
- ~42% of Anthropic's ~11GW contracted compute is NVIDIA GPUs — ns123abc · 2026-10-27
- RTX 5080 price jumps from $1658 to $2318 in ten days on Amazon — Frizzy-MacDrizzle · 2026-10-27
- ComfyUI on 12GB VRAM: measured peaks show offloading turns 24s into 11 minutes — Impossible-Mail-4619 · 2026-10-27