Matching stories Newest first
Eagle-4 speculative decoding method reported faster than DFlash2 and DSpark on Qwen3.8-27B
80x. cpp and vLLM support later.
ISTA-DASLab releases a Qwen3.8-27B prefiller model that streams from SSD for low-quant accuracy
The demo recovers accuracy for low-bit quantized Qwen3.8-27B while keeping VRAM usage low and decoding fast. It reportedly needs an Nvidia Blackwell GPU, and the poster has not tested it. For context longer than about 4k tokens, the poster expects no speed penalty.
Tess-4.5-27B, a Qwen finetune, claims 25% fewer tokens at the same score
Community finetune by migtissera built on Qwen3.8-27B, with GGUF files on Hugging Face. The author reports 25% fewer tokens across 150 BenchLocal scenarios and 43% fewer on data extraction, with the same scores claimed.