BREAKING
1B Model Distilled From Claude Fable 5
Frontier Reasoning, Offline Footprint
0MB
Q4_K_M size
0GB
Q8_0 recommended
0K
context tokens
Quantized Build Sizes
Q4_K_M657
Q5_K_M751
Q8_01100
F162100
Runs Local, But Has Limits
StrengthsApache-2.0
Runs on llama.cpp, Ollama, LM Studio
Thinking mode with chain-of-thought
V2 build adds tool-calling
Cautions
Limited on complex tasks
Thinking output can be verbose
Independent benchmarks still limited
Compressing Frontier AI Locally
AI NEWS BLITZ
A tiny one-billion-parameter model trained on Claude Fable 5 reasoning is now out in GGUF.