Solstice-AI/Qwopus3.8-27B-Flash-GGUF-1M

feat: update tokenizer_config chat_template to Solstice 10-level solo + swarm

feat: update to Solstice 10-level solo + swarm cognitive architecture

docs: update quant matrix with official Q6_K, Q5_K_M, and Q5_K_S additions

Copy files from models/Jackrong/Qwopus3.8-27B-Flash-GGUF

Copy files from models/Jackrong/Qwopus3.8-27B-Flash-GGUF

Copy files from models/Jackrong/Qwopus3.8-27B-Flash-GGUF

docs: add streamlined model card

feat(speculative): add companion 27B DSpark drafter

feat(gguf): add Unsloth Dynamic v3.0 mmproj-BF16.gguf

feat(gguf): add Unsloth Dynamic v3.0 Qwopus3.8-27B-Flash-UD-Q8_K_XL-1M.gguf

fix(tokenizer): set model_max_length to 1048576 (1M context)

feat(gguf): add Unsloth Dynamic v3.0 Qwopus3.8-27B-Flash-UD-Q6_K_XL-1M.gguf

feat(gguf): add Unsloth Dynamic v3.0 Qwopus3.8-27B-Flash-UD-Q4_K_XL-1M.gguf

feat(gguf): add Unsloth Dynamic v3.0 Qwopus3.8-27B-Flash-UD-IQ4_XS-1M.gguf

feat(tokenizer): update tokenizer_config with dynamic reasoning controls

feat(tokenizer): add dynamic adjustable thinking template (enable_thinking & reasoning_effort)

initial commit