Qwen3.8-27B (bf16 source, ssmfix chat template applied) quantized with a per-tensor mixed scheme derived from GSQ grid learning + RCO Riemannian tangent-projection search. Search domain {2,3,4} bit, target avg ~3.5 bpw; result: IQ3S-dominant mix (IQ3S=144, IQ4XS=96, IQ3XXS=78 tensors), avg bpw 3.52, 866 tensors, 12.0 GB. Built with llama-quantize + imatrix (fineweb-edu style corpus) from the bf16 -> f16 GGUF (converthftogguf.py). Includes MTP head; pair with mmproj-Qwen3.8-27B-Q5K-MIX for vision. Measured on RTX 3080 20G (llama-kvmem-server, kv q80, draft-mtp n=3): decode ~48.5 t/s, prefill ~1150 t/s.
Independent publisher
Sky
redashes
Models in Library1
Datasets in Library0
Models on Hugging Face4
Followers5
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Any to any.
Reported licenses: apache-2.0. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.