BTL-3 27B agentic coding and tool-use model from Bad Theory Labs (fits in 8.39GB)

https://x.com/Badtheorylabs/status/2079306502897074249 A 27B open-weight agent model built for agentic coding, structural tool use . The complete thing fits in one 8.39GB file under 2.5 bits per parameter smaller than an 8B model in fp16, and retains 92.2% of the 27B intelligence. BTL-3 is trained for the loop real agents live in: reason, act, inspect the result, recover, continue. It handles single, sequential, and parallel tool calls and knows when the right move is no tool call at all. HumanEval: 95.12% pass@1 BFCL v4 AST: 88.5% (full 1,240-case set) Multiple tool calls: 95.5% Tool-call abstention: 91.2% 262K context architecture Two editions, both open today. BTL-3 is the maximum-quality checkpoint, for Transformers and vLLM. BTL-3 Compact is the entire model in one standalone 8.39GB GGUF. No base download. No reconstruction. One file, one command, a running agent Compressing 27B this far normally destroys a model. Standard quantization couldn't do it, so we built the stack ourselves: packed AVQ2 decoder tensors, affine INT4, measured precision islands, packed vocabulary matrices, rank-32 output correction, behavioral repair. 2,416 tensors byte-verified at export. Then we tested whether the agent survived. On a fresh sealed 100-turn tool-contract gate, Compact retained 92.2% of teacher-correct behavior 100% on single, parallel, sequential, and abstention calls. 43 tok/s generation on an RTX PRO 6000. Fully local. Nothing leaves your machine. BTL-3: https://huggingface.co/badtheorylabs/ BTL-3 Compact: https://huggingface.co/badtheorylabs/ BTL-3-Compact Runtime + source: https://github.com/Badtheorylabs/ BTL-3 Apache-2.0 model. MIT runtime.