跳到主要内容Skip to main content
投机取巧 Speculative Speculation

PoolsidePoolside　·　当前代current generation Laguna 2.1 / XS.2Laguna 2.1 / XS.2（2026-08）

LagunaLaguna模型家族谱系卡model family lineage card

代码专用家族里许可最宽的一族（OpenMDW-1.1 完全宽松）；主打「本地机器跑 agentic coding」，激活 3B 是它的本地性来源。本站收录 Laguna XS-2.1 的量化对比。The most permissively licensed coding line (OpenMDW-1.1, fully permissive); its pitch is agentic coding on a local machine, with 3B active parameters as the source of that locality. This site covers Laguna XS-2.1 quantisations.

本站已收录该家族的量化对比：This site covers this family's quantisations: Laguna 2.1Laguna 2.1

先说清楚：这个站的数据怎么来的First, where this site's data comes from

✅ 实测字段Measured fields

直接从 Hugging Face 公开 API 读取的客观数据：文件体积（字节）、上下文长度、架构、许可、下载量、更新时间。Objective data read straight from the Hugging Face public API: file sizes in bytes, context length, architecture, licence, downloads, last updated.

✅ 推导Derived

由实测字段按公开规则算出：每权重比特数（依 llama.cpp 命名标准）、档位归属、显存需求区间。推导规则在Computed from the measured fields by published rules: bits per weight (per the llama.cpp naming convention), tier assignment, VRAM requirement range. The rules are fully published in METHODOLOGY.md 完整公开，任何人可复算。 — anyone can recompute them.

❌ 我们不说的What we do not claim

哪个量化质量更高、哪个更快、哪个模型更强——这些需要实测，本站不跑 benchmark，所以不装作知道。凡我们给出的主观判断，一律显式标注「我们的口径」。Which quantisation is higher quality, which is faster, which model is stronger — these need measurement. This site does not run benchmarks, so it does not pretend to know. Every subjective judgement we do offer is explicitly marked as our own reading.

本站This site does 不下载、不托管任何模型权重文件not download or host any model weight files。所有数字都来自公开元数据，点击即可回到发布页核对。. Every figure comes from public metadata, and clicking it takes you back to the release page to verify. 采集时间Collected: 2026-10-30（数据快照，非实时） (a snapshot, not live)

中文生态China availability 国产 / 国内可直接用 / 备案状态 · 快照domestic / direct access / CAC filing · snapshot 2026-10-20

  • 出品属地Origin　国外出品foreign-made　出品方为 Poolside。Made by Poolside.
  • 国内下载Direct access　国内可直连direct OK　ModelScope 有 poolside 官方组织镜像（2026-10-20 实测 200）；Hugging Face 直连不可达。ModelScope carries the official poolside org mirror (measured 200); Hugging Face direct unreachable.　·　国内镜像入口domestic mirror
  • 备案状态CAC filing　未见于备案名单not in filing list：公示名单未检索到 Poolside / Laguna 相关条目（2026-10-20）。No Poolside / Laguna entry found in the public registry (searched 2026-10-20).

备案信息以网信办《生成式人工智能服务已备案信息》公示名单为准（按批次滚动更新，本站只抄编号不解读）；「国内可直连」是本站从大陆网络直连实测的结果，不是厂商承诺。Filing status is quoted from the CAC public registry (updated batch by batch; this site copies the number and does not interpret it). "Direct access" is this site's own reachability measurement from a mainland network, not a vendor promise.

代次Generations

  • Laguna 2.1 系Laguna 2.1 line2026-06–08

    当前代线：XS-2.1（33B 总参 / 3B 激活，262,144 token 上下文）、S-2.1、M.1 等在官方 org 在册；官方 README 称 XS 2.1 相对 XS.2 在 SWE-bench Multilingual +5.4%（厂商自评口径）。Current line: XS-2.1 (33B total / 3B active, 262,144-token context), S-2.1, M.1 and more in the official org; the README claims XS 2.1 gains +5.4% over XS.2 on SWE-bench Multilingual (vendor-run wording).

    官方页面 ↗official page ↗
  • Laguna XS.2Laguna XS.22026

    上一档（XS.2 及其 FP8/NVFP4/INT4 变体在册）。The previous step (XS.2 with FP8/NVFP4/INT4 variants listed).

    官方页面 ↗official page ↗

尺寸档Size tiers

  • 本地 XS（33B 总参 / 3B 激活，官方称 36GB Mac 可跑）Local XS (33B total / 3B active; the vendor says a 36GB Mac runs it)
  • 更大档 S / M（官方 org 在册）Larger S / M builds (official org)

许可Licences

  • openmdw-1.1OpenMDW-1.1（官方 README：「a fully permissive license. Use it, modify it, and build commercial products on it. No permission required.」）OpenMDW-1.1 (official README: "a fully permissive license. Use it, modify it, and build commercial products on it. No permission required.") 许可原文 ↗licence text ↗

官方能力声明（带出处）Official capability claims (with sources)

  • 官方 README：「33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine」「Context window: 262,144 tokens」；Ollama 与 llama.cpp 官方收录。Official README: "33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine"; "Context window: 262,144 tokens"; listed in Ollama and llama.cpp.出处 ↗source ↗

以上均为厂商官方页面原文或官方自评基准的转述；涉及横评结论的，本站不背书——本站不跑 benchmark。The above are quotations of official pages or transcriptions of vendor-run benchmarks; this site does not endorse cross-model conclusions — it runs no benchmarks.

出处Sources

核验快照：2026-10-30 · 本站不实测、不排名，未知就写未知。Verification snapshot: 2026-10-30 · no benchmarks, no rankings — unknown stays unknown.