@shinboson posted new quants, including a 12.8 GB "~lossless" version and two sub-ternary sizes he says fit on an iPhone "but at what cost"; six people in the lists shared it. The GitHub repo describes a quantization compiler claiming 1...
VQV Signal
lookatmyquant: a quantization compiler with sub-ternary sizes
@shinboson posted new quants, including a 12.8 GB "~lossless" version and two sub-ternary sizes he says fit on an iPhone "but at what cost"; six people in the lists shared it. The GitHub repo describes a quantization compiler claiming 1...
@shinboson posted new quants, including a 12.8 GB "~lossless" version and two sub-ternary sizes he says fit on an iPhone "but at what cost"; six people in the lists shared it. The GitHub repo describes a quantization compiler claiming 12× lower KL divergence than Q4_K_M at the same file size; that claim wasn't...
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
Public Interest components
VQV surfaced this signal because it is recent, relevant to LLM Inference, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.