{"pubkey":"9bc96cec032d546cf1ce276a23af195a1a92cda0b6745ecf8e7d4341828fc423","posts":[{"contentHash":"1f079f5dbccf367f0e9caf5d06de85663a16809384f573756cae61a3481b7902","protocol":"bitcoin","authorPubkey":"9bc96cec032d546cf1ce276a23af195a1a92cda0b6745ecf8e7d4341828fc423","text":">Really wish a modern 16-20B dense model existed. I think 20B should be /the/ target size for well-trained local dense models running on single consumer GPUs. It's a good size for 16GB (in 4-bit) and 24GB (in 6~8-bit) GPUs. More parameters could be added as Engram layers / PLE.","topicHash":"913c62c2ee31793c7e8517600dbc8f0c337afae133700a128a7d8ffb8a21c93e","topicName":"technology","parentHash":"0c128947034f5ac41c07f91d0b461d2db9f955d906fe8fd75f189dfe2ecc6025","costSunk":"0","biasSupport":0,"biasOppose":0,"biasVouch":0,"biasNull":0,"blockHeight":null,"confirmations":0,"timestamp":"2026-11-07T10:05:20.273Z","tripFp":"d24ec68941d0","viewCount":0,"powDifficulty":0,"relation":0,"ephemeral":true,"nonce":"186f4a9b7ac129fa","sig":"f59c542ed371466275681725c4ab498eda7981ebb4ecb580b6b5ab11bb1f578a33c269e7421ee0f31a63e1d70f585e2a62f35500e91406db3344f16b142738d9","ephStamp":{"blockHashHex":"00000000000000000000f56d7df631ac544b45faa8c704cc3664ce88f8a98106","nonceHex":"9fe1020000000000"},"replyCount":0,"chainReplyCount":0,"vaporReplyCount":0,"clusterSize":1,"receiptHeight":974917,"expiryHeight":975925,"authorMarks":{"since":"2026-11-07T10:05:20.316Z","via":"sight","inscribed":0,"likes":0,"biases":0},"lang":"en"}],"nextCursor":null,"pageReceipt":{"host":"6af58b1822e0cabfe57d76540f745d059b438f489a796ec6a705c6540233845e","t":"2026-11-08T20:11:13.385Z","sig":"10d54bdddae80e5f5332d397e94ebe5a9056dd78615edc133685fca967707340cb6ce3f2b2d358d85fdda029f3ebe8968158dd290488ba79b80db5d9810a4769"},"marks":{"since":"2026-11-07T10:05:20.316Z","via":"sight","inscribed":0,"likes":0,"biases":0}}