Skip to page content
SAVRN
Search Plan a project

Independent publisher

Qinghua

liqinghhua

Models in Library1
Datasets in Library0
Models on Hugging Face3
Followers2

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.

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.

Models

本仓库是什么:把官方 occamy-1.0(35B-A3B MoE + 视觉编码器)与官方 occamy-1.0-MTP 草稿头合并进同一份权重(mtpnumhiddenlayers: 1),再用 oMLX 的 oQ6e 量化导出,专供 Apple Silicon 上的 oMLX 推理。非官方发布,未经 Accio-Lab 验证。 - 实测(本机真实使用日志,113 次请求,Mac Studio M4 Max 64GB):草稿接受率 77.95%(48,501/62,218),分深度 d1 79.4% / d2 76.3% / d3 77.3%;中位 2.83 tokens/cycle;中位解码 110.5 tok/s(p10 78.0 / p90 146.9)。工具调用类结构化输出接受率 85.7%,自由文本 75.8%。 - 量化配方:oQ6e = oMLX 通用动态量化,6-bit 基准(专家层 6-bit/group 64;语言部分 ≈6.6 bpw,整文件含视觉塔 ≈6.7 bpw);嵌入、注意力/GDN 投影、共享专家提升到 8-bit;全模型 norms、MoE 路由、MTP 融合层与整个视觉塔保持未量化;imatrix 校准(oqecodemultilingual,128×512,专家覆盖 100%)。 - 体积:30.28 GB(28.20 GiB),6 个分片;64GB 统一内存可运行(实测占用约 29 GB)。 Upstream ships the MTP draft head as a separate artifact that must be…

Open weights apache-2.0 36B parameters 262,144 tokens mlx