EdgeRock-4B open-sourced with fixed 72MiB KV cache, 99.1% less memory than base
testingcatalog · x · 2026-10-31
Rock Matrix has open-sourced EdgeRock-4B, a small text-and-image reasoning model with fixed-capacity memory. Its attention KV cache stays constant in size — the last 1,024 tokens are kept in full while older important details go to a separate retrieval bank (Rock Memory Anchors), avoiding the unbounded KV growth of standard LLMs during long chats and reasoning.
- Scores 82.9% mean pass@1 on AIME 2024–2026 vs 18.8% for the strongest bounded-state model tested
- KV cache capped at 72 MiB per conversation vs 8 GiB for the base at 256K tokens (99.1% less)
- Weights on Hugging Face and ModelScope, plus NF4/INT8/FP8 quantized versions
Related event: Rock Matrix Open-Sources EdgeRock-4B with Constant-Memory KV Cache(3 posts)→
More from Models
- 5 cheap open models vote vs Opus: 89.6% accuracy at 1/10th the cost — PomegranateAble4339 · 2026-10-31
- Gemini 4 Carbon reportedly scores 53 FCI on FrontierCS 2, big jump from Argon in weeks — clmt · 2026-10-31
- Gemini 3.5 Pro reportedly delayed into oblivion while rivals took share, says dev — tarantulae · 2026-10-31
- Dev suspects longer training degraded Qwen backbone multilingual abilities, plans more multilingual data — antoine_chaffin · 2026-10-31
- LiquidAI's LFM3-VL d1-2B edge vision-language model trends on Hugging Face — LiquidAI · 2026-10-31
- OpenAI's new API credits make ChatGPT Pro tiers a no-brainer for API users — Quiet-Recording-9269 · 2026-10-31