iapp/openthai2.0-qwen3.8-27b-GGUF

v2.0.2 GGUF

v2.0.2 GGUF

v2.0.1 GGUF (Q8_0 / Q4_K_M / IQ2_M+imatrix / mmproj)

Add importance matrix for community re-quants

Add IQ2_M (imatrix-calibrated 2-bit; MTP layer q8_0)

README: IQ2_M recommended 2-bit + imatrix note

README: Q2_K row with quality warning

Add Q2_K 2-bit quantization

Re-quantized from release winner

Title: Knowledge, Document, and Agentic AI

GGUF card

Add mmproj-openthai2.0-qwen3.8-27b-F16.gguf (v9, MTP head included)

Add openthai2.0-qwen3.8-27b-Q8_0.gguf (v9, MTP head included)

Add openthai2.0-qwen3.8-27b-Q4_K_M.gguf (v9, MTP head included)

initial commit