MODEL PROFILE · 模型档案

Ornith-1.0-9B-MTP-GGUF

protoLabsAI · Ornith-1.0-9B-MTP-GGUF

GGUF builds of `deepreinforce-ai/Ornith-1.0-9B` with the KL-distilled MTP draft head from `protoLabsAI/Ornith-1.0-9B-MTP` **baked into the trunk** — llama.cpp does lossless multi-token self-speculative decoding out of the box, no separate draft model to wire up. Every file here carries the `nextn` head, so `--spec-type draft-mtp` just works. "Bundled" = trunk + `nextn` head in one file. The **IQ** rungs are i-quants (importance-matrix calibrated) with the **MTP head pinned to Q8_0** so acceptance holds on the low-bit trunk (measured ~0.81–0.84 on IQ2_M–IQ4_XS, on par with the k-quants). Serve them exactly like the k-quants. The standalone head is **not a model** — loading `mtp-head/…` directly will crash. It exists only to pair with a base Ornith-9B GGUF via `--model-draft`.

译文排队中,当前展示来源原文。

文本生成license:mit
上下文窗口来源未披露
输入 → 输出文本 → 文本
模型权重待核验
档案更新时间2026/11/2 19:16:11
OVERVIEW

模型介绍

GGUF builds of `deepreinforce-ai/Ornith-1.0-9B` with the KL-distilled MTP draft head from `protoLabsAI/Ornith-1.0-9B-MTP` **baked into the trunk** — llama.cpp does lossless multi-token self-speculative decoding out of the box, no separate draft model to wire up. Every file here carries the `nextn` head, so `--spec-type draft-mtp` just works. "Bundled" = trunk + `nextn` head in one file. The **IQ** rungs are i-quants (importance-matrix calibrated) with the **MTP head pinned to Q8_0** so acceptance holds on the low-bit trunk (measured ~0.81–0.84 on IQ2_M–IQ4_XS, on par with the k-quants). Serve them exactly like the k-quants. The standalone head is **not a model** — loading `mtp-head/…` directly will crash. It exists only to pair with a base Ornith-9B GGUF via `--model-draft`.

主要特点

特点摘要待依据来源补齐,不凭模型名称推断能力。

局限与注意事项

暂无足够来源支持具体缺点结论。请重点验证实际任务表现、时延、数据政策、许可与版本生命周期。

PRICING & COST

来源报价与费用分析

同一模型在不同渠道、地区和配置下可能采用不同价格。下表独立保留各渠道报价,不将渠道价格视为厂商官方统一价格。

来源 / 渠道输入输出计费单位采集时间
暂未取得可核验报价,请查阅来源渠道。

按月估算基础 Token 费用

—

预估不包含缓存优惠、阶梯定价、多模态附加费用、网络检索、税费及推理额外输出。

INDEPENDENT BENCHMARKS

公开评测与运行配置

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

查看完整已收录榜单 →

常见问题

开放权重是否代表可以免费商用?

不一定。应核对具体版本许可证、商用门槛和使用政策。自部署还会产生算力和维护成本。

这些价格是实时结算价格吗?

不是实时结算价格,而是带采集时间的来源报价快照。请到对应渠道核对当前版本、区域、折扣和计费方式。

资料来源与可追溯记录

许可证:mit。模型介绍与第三方评测均以原来源的具体版本和方法为准。