Hy3 (295B MoE) and NVIDIA Nemotron-Labs-Audex-30B-A3B (audio-capable 30B MoE) GGUF quants
英文标题：Hy3 (295B MoE) and NVIDIA Nemotron-Labs-Audex-30B-A3B (audio-capable 30B MoE) GGUF quants
Sharing two GGUF quant sets, both with the same treatment: imatrix quantization, KLD/PPL measured against BF16 reference logits, llama-bench throughput numbers, and all raw benchmark data included in the repos. No vibes-based "quality tested" claims — every number is reproducible from the files in t
打开原文相关 2 · 机会 0
中文
Sharing two GGUF quant sets, both with the same treatment: imatrix quantization, KLD/PPL measured against BF16 reference logits, llama-bench throughput numbers, and all raw benchmark data included in the repos. No vibes-based "quality tested" claims — every number is reproducible from the files in t
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
Sharing two GGUF quant sets, both with the same treatment: imatrix quantization, KLD/PPL measured against BF16 reference logits, llama-bench throughput numbers, and all raw benchmark data included in the repos. No vibes-based "quality tested" claims — every number is reproducible from the files in t