AI NEWS.ccAI正在发生 未来正在更新
♡ 我的收藏 0
AI 模型库/Yamada114514/AliceAI-Foundation-80B-A3B-Base-GGUF
MODEL PROFILE · 模型档案

AliceAI-Foundation-80B-A3B-Base-GGUF

Yamada114514 · AliceAI-Foundation-80B-A3B-Base-GGUF

**Requires the custom llama.cpp patch in this repository. Stock llama.cpp, Ollama and LM Studio have NOT been validated with this new `aliceai` architecture. Do not expect this file to work by simply importing it into an unmodified app.** This is a community conversion, not an official Yandex release. It is an 80B-parameter MoE **Base completion model**, not an instruction-tuned assistant. MTP is **not implemented**; the source MTP module is omitted. No training, fine-tuning, distillation or additional alignment was performed. - `AliceAI-Foundation-80B-A3B-Base-Q4_K_M.gguf`: **48,421,862,304 bytes (45.10 GiB)**, 1,167 tensors, approximately 4.86 bits/weight. - Converted directly from the original BF16 source, **not requantized from MLX Q4**. - Source: yandex/AliceAI-Foundation-80B-A3B-Base, revision `b7984f62fd212535d2de9094bfeba23de58cd7c8`. - Runtime base: ggml-org/llama.cpp, commit `7ab4ee7baad2d920464cbacfad4f4b07cf111fd2`, plus `aliceai-llama.cpp.patch`. - Q4_K_M uses mixed tensor precision, including Q6_K. In addition, **72 small KDA projection tensors use Q5_0**, because their width of 128 cannot use 256-element K-quant blocks. Norms, router weights, depth-residual scores and convolution weights retain FP32. This is not an all-tensors-exactly-4bit model. - The inherited GGUF display name is `Source`; identify the model by its file name and use `--alias AliceAI-80B-A3B-Q4` if desired. This label does not affect weights.

译文排队中，当前展示来源原文。

文本生成license:apache-2.0
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 19:16:30
OVERVIEW

模型介绍

**Requires the custom llama.cpp patch in this repository. Stock llama.cpp, Ollama and LM Studio have NOT been validated with this new `aliceai` architecture. Do not expect this file to work by simply importing it into an unmodified app.** This is a community conversion, not an official Yandex release. It is an 80B-parameter MoE **Base completion model**, not an instruction-tuned assistant. MTP is **not implemented**; the source MTP module is omitted. No training, fine-tuning, distillation or additional alignment was performed. - `AliceAI-Foundation-80B-A3B-Base-Q4_K_M.gguf`: **48,421,862,304 bytes (45.10 GiB)**, 1,167 tensors, approximately 4.86 bits/weight. - Converted directly from the original BF16 source, **not requantized from MLX Q4**. - Source: yandex/AliceAI-Foundation-80B-A3B-Base, revision `b7984f62fd212535d2de9094bfeba23de58cd7c8`. - Runtime base: ggml-org/llama.cpp, commit `7ab4ee7baad2d920464cbacfad4f4b07cf111fd2`, plus `aliceai-llama.cpp.patch`. - Q4_K_M uses mixed tensor precision, including Q6_K. In addition, **72 small KDA projection tensors use Q5_0**, because their width of 128 cannot use 256-element K-quant blocks. Norms, router weights, depth-residual scores and convolution weights retain FP32. This is not an all-tensors-exactly-4bit model. - The inherited GGUF display name is `Source`; identify the model by its file name and use `--alias AliceAI-80B-A3B-Q4` if desired. This label does not affect weights.

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

huggingface · Yamada114514/AliceAI-Foundation-80B-A3B-Base-GGUF ↗2026/11/1 22:05:01
huggingface · enrich:ef8a5f06-1a1e-4259-b5ab-6799621a28dc ↗2026/10/29 22:56:52

许可证：apache-2.0。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。