EmbeddingGemma 2 Edge — Quantization - a ThakiCloud Collection

ThakiCloud 's Collections

EmbeddingGemma 2 Edge — Quantization

RAG-Gate — Answer / Retrieve / Stop Gates for RAG

ChainCheck — Chain-Sensitive Evidence Judges

PACE — Enterprise Policy Decisions: Learned or Reasoned

Merchant Desk — Korean Small-Business Customer Desk

Qwen-Image-2.1 — Few-Step Distillation

K-Decision — Korean typed-decision adapters (weights only)

K-MT — Korean-Specialized Translation Without Forgetting

Satoori-KO — Korean Regional Dialect 27B

Evals & Reproducibility

Language Confusion Suppression — Vocabulary Pruning

Vision-Language — Serving Quantization

Qwen3-30B-A3B — Serving Quantization

Qwen3-Coder-30B-A3B — Serving Quantization

Qwen3.8-27B — Serving Quantization

SkillRet — Agent Skill Retrieval

Human-KO — Korean Style-Aligned 27B

EmbeddingGemma 2 Edge — Quantization

updated about 2 hours ago

Quantized EmbeddingGemma 2 text towers that query an existing BF16 index without re-embedding the corpus.

ThakiCloud/eg2-text-q4

Feature Extraction • 0.1B • Updated about 16 hours ago

Note 4-bit text tower, 152,669,232 B of weights. Keeps 0.936 of the BF16 top-10 neighborhood (BF16 = 1.000); margin 0.1712 vs BF16 0.1817. Internally measured on a private frozen set; serving not validated.
ThakiCloud/eg2-text-hybrid-129m

Feature Extraction • 0.1B • Updated about 2 hours ago

Note Mixed-precision text tower (GPTQ 4-bit transformer, 2-bit vocabulary with 30% of rows at 4-bit), 129,532,796 B — 85% of eg2-text-q4. Beats uniform 3-bit on every held-out slice; within 25% of the 3→4-bit gap of the Q4 recipe. Internally measured; serving not validated.