TAF Agent - 25 browser-only LLM diagnostics (does your quant still work?)

#2
by karlexmarin - opened

GGUF/VRAM calculators tell you if a model fits. None tell you if it still works after the quant or the RoPE/YaRN context-extension. TAF Agent runs 25 diagnostics fully in-browser (WebGPU) - quantization drift, long-context degradation (RULER/NIAH-style), chat-template sanity, KV-cache, contamination/arena-elo - no GPU, no signup, no telemetry. 4 languages.

Backed by a dataset (58 measurements / 32 models) and 37 Lean+Mathlib-verified theorems.

Feedback welcome from anyone who runs quants locally - where does "fits but broken" bite you? Bug reports and mode requests go here.

Sign up or log in to comment