ggml-org Releases Qwen3.8-27B-GGUF with Agent and Speculative Sampling

ggerganov · x · 2026-08-15

ggml-org released the Qwen3.8-27B-GGUF model in Q4 quantizations on DGX Spark. The demo command showcases features like speculative sampling (draft-mtp), default specs, and a reasoning-preserving agent mode.

Related event: Community Shares Qwen3.8-27B Deployment on 32GB VRAM(4 posts)→

Original post →

More from Models

Models channel →