VnimanieAI/Qwen3.8-Flash-Next-W4A16
306.1k
Recommend cyankiwi AWQ for 8x24GB setups; add head-to-head results; attribute verbosity to quant recipe
Correct GPQA budget-corrected accounting (0.854 -> 0.874); clarify hosted reference
Add capability benchmarks (tau2-bench Airline, MMLU_RU, GPQA Diamond)
library_name transformers: enable Hub vLLM app-compatibility (transformersInfo)
Add 4-bit tag for Hub precision filter
Upload folder using huggingface_hub
Upload LICENSE with huggingface_hub
Upload README.md with huggingface_hub
Add files using upload-large-folder tool
initial commit
