{"id":"botpsy-0-8b","slug":"botpsy-0-8b","name":"BotPsy-0.8B","orgId":"qvac","family":"botpsy-0-8b","releaseDate":null,"availability":"ga","openWeights":true,"license":"Apache License 2.0 (model card and LICENSE file)","paramsTotal":800000000,"paramsSource":"slug","contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/blog/qvac/botpsy","hfRepo":null,"modalities":["text"],"aliases":["BotPsy-0.8B","botpsy-0-8b","BotPsy","botpsy","QVAC BotPsy","qvac botpsy","qvac/BotPsy-0.8B","qvac/BotPsy-0.8B-GGUFs"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-11-11","announced":"2026-11-11","blurb":"QVAC (Tether AI Research)'s 0.8B-parameter language model for function calling and agentic workflows, post-trained from Qwen3.5-0.8B for on-device use as a personal assistant. Announced November 11, 2026. Public Apache 2.0 weights are on Hugging Face as BF16 safetensors, with BF16, Q8_0 and Q4_K_M GGUF builds for llama.cpp and the QVAC SDK. No hosted API is offered.","api":"none","openWeights":"yes","params":{"text":"0.8B","source":"QVAC BotPsy Hugging Face blog and model card"},"facts":[{"label":"Type","value":"Causal language model for tool calling (Qwen3.5 architecture: hybrid Gated DeltaNet plus gated attention), used text-only, with thinking mode (QVAC model card)"},{"label":"Base","value":"Post-trained from Qwen3.5-0.8B in four stages: supervised fine-tuning, multi-teacher on-policy distillation, and two reinforcement-learning rounds (QVAC blog)"},{"label":"Language","value":"English is recommended; also evaluated on Multi-IF in seven other languages (QVAC blog)"},{"label":"Weights","value":"Public, ungated Hugging Face repo qvac/BotPsy-0.8B (BF16 safetensors). GGUF builds (BF16, Q8_0, Q4_K_M) in qvac/BotPsy-0.8B-GGUFs"},{"label":"License","value":"Apache License 2.0 (model card and LICENSE file)"},{"label":"API","value":"None; the weights run locally"},{"label":"Related","value":"Separate from VisionPsy-Nano-460M (same lab) and from the Qwen3.5-0.8B base model"}],"claims":["Lab claim: self-reported BFCL v4 44.0, ACEBench 58.7, and τ-bench 51.5, compared with 23.4, 30.1 and 23.2 for the Qwen3.5-0.8B-Think base (QVAC blog and model card).","Lab claim: self-reported IFEval 90.8 and IFBench 55.9, compared with 59.7 and 22.0 for the Qwen3.5-0.8B-Think base (QVAC blog and model card)."],"sources":[{"kind":"lab","title":"QVAC Hugging Face blog: BotPsy","url":"https://huggingface.co/blog/qvac/botpsy","date":"2026-11-11"},{"kind":"repo","title":"qvac/BotPsy-0.8B on Hugging Face","url":"https://huggingface.co/qvac/BotPsy-0.8B"},{"kind":"repo","title":"qvac/BotPsy-0.8B-GGUFs on Hugging Face","url":"https://huggingface.co/qvac/BotPsy-0.8B-GGUFs"}],"firstBenchmark":null},"organization":{"id":"qvac","name":"QVAC (Tether)","slug":"qvac","country":null,"url":"https://qvac.tether.io","color":"#11110F","mark":"Q"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Nov 11, 2026; no independent results yet.","lead":"As of Nov 22, 2026, BotPsy-0.8B is pending benchmarks on isitsota: announced Nov 11, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}