27B reasoning with ternary weights.
Ternary Bonsai 2 27B is now on NanoGPT, included in the subscription.
PrismML reports 98.2% of Qwen3.8-27B's aggregate benchmark performance. With vision, tool calling and a 262K context window.
https://nano-gpt.com/conversation?model=prism-ml%2Fternary-bonsai-2-27b
nanogpt / NanoGPT
npub1v2…e3fn9
2026-09-19 11:02:57 UTC
Author Public Key
npub1v2fdmse57a5jddq7aenmlcuj97n6867fm55kktp6uq5lt6m409fsle3fn9Published at
2026-09-19 11:02:57 UTCEvent JSON
{
"id": "27f104e83ea38c4e1a6206c6198127f2991216b7598d3c50739a7b0d7e9dab74",
"pubkey": "6292ddc334f76926b41eee67bfe3922fa7a3ebc9dd296b2c3ae029f5eb757953",
"created_at": 1789815777,
"kind": 1,
"tags": [
[
"t",
"prismml"
],
[
"t",
"bonsai"
],
[
"t",
"ai"
],
[
"t",
"nanogpt"
],
[
"t",
"llm"
],
[
"t",
"aiagents"
],
[
"r",
"https://nano-gpt.com/conversation?model=prism-ml%2Fternary-bonsai-2-27b"
]
],
"content": "27B reasoning with ternary weights.\n\nTernary Bonsai 2 27B is now on NanoGPT, included in the subscription.\n\nPrismML reports 98.2% of Qwen3.8-27B's aggregate benchmark performance. With vision, tool calling and a 262K context window.\n\nhttps://nano-gpt.com/conversation?model=prism-ml%2Fternary-bonsai-2-27b",
"sig": "1e358f2e9bde8b4b4ddc7527b9a357c2b73a279f59e1398c67850fe125a67a15b5a6c8480169461cb5a8aa08bb973dc92eb519be837965e95a74a26d608321c3"
}