docs: make Chinese README the default

2026-07-13 10:18:43 +00:00
parent 8a27026245
commit 99cec097b6
1 changed files with 154 additions and 173 deletions
@@ -1,3 +1,9 @@
+<!-- WEHUB_ZH_README -->
+> [!NOTE]
+> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。  
+> [English](./README.en.md) · [原始项目](https://github.com/Andyyyy64/whichllm) · [上游 README](https://github.com/Andyyyy64/whichllm/blob/HEAD/README.md)  
+> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。
+
 # whichllm

 [![PyPI version](https://img.shields.io/pypi/v/whichllm)](https://pypi.org/project/whichllm/)
@@ -10,65 +16,62 @@
  <a href="https://trendshift.io/repositories/30336" target="_blank"><img src="https://trendshift.io/api/badge/repositories/30336" alt="Andyyyy64%2Fwhichllm | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 </p>

-**Find the best local LLM that actually runs on your hardware.**
+**找到真正能在你硬件上运行的最佳本地 LLM。**

-Auto-detects your GPU/CPU/RAM and ranks the top models from HuggingFace that fit your system.
+自动检测你的 GPU/CPU/RAM，并从 HuggingFace 中按适配度对适合你系统的顶级模型进行排名。

 [日本語版はこちら](docs/README.ja.md)

-## Quick start
+## 快速开始

-Run the recommendation command once, with no project setup.
+无需项目配置，运行一次推荐命令即可。

 ```bash
 uvx whichllm@latest
 ```

-Simulate a GPU before you buy hardware.
+在购买硬件之前模拟 GPU。

 ```bash
 uvx whichllm@latest --gpu "RTX 4090"
 ```

-Install it when you use it often.
+若经常使用，可安装到本地。

 ```bash
 uv tool install whichllm
 uv tool upgrade whichllm  # update an existing install
 ```

-Other install paths.
+其他安装方式。

 ```bash
 brew install andyyyy64/whichllm/whichllm
 pip install whichllm
 ```

-## Want a safer pick?
+## 想要更稳妥的选择？

-By default, whichllm is ambitious. It ranks the best model that looks runnable
-on your machine, including partial RAM offload and near-edge VRAM fits when
-they seem usable.
+默认情况下，whichllm 较为激进。它会对你机器上看起来可运行的最佳模型进行排名，包括部分 RAM 卸载（offload）以及看似可用的接近显存上限的 VRAM 配置。

-If you want a more comfortable LM Studio-style recommendation, start with:
+若你想要更接近 LM Studio 风格的舒适推荐，可从以下方式开始：

 ```bash
 uvx whichllm@latest --gpu-only --speed usable --vram-headroom 1GB
 ```

-This keeps only models that fit fully in GPU VRAM, filters out slow estimates,
-and leaves extra VRAM for runtime overhead.
+这样只会保留完全装入 GPU VRAM 的模型，过滤掉速度较慢的估算结果，并预留额外 VRAM 以应对运行时开销。

-If LM Studio still says the model is slightly too large, increase the headroom:
+若 LM Studio 仍提示模型略大，可增加余量：

 ```bash
 uvx whichllm@latest --gpu-only --speed usable --vram-headroom 1.5GB
 ```

-## Common workflows
+## 常见工作流

-After install, run `whichllm` directly. For one-off runs, replace `whichllm`
-with `uvx whichllm@latest`.
+安装后，直接运行 `whichllm`。若只需一次性运行，将 `whichllm`
+替换为 `uvx whichllm@latest`。

 ```bash
 # Best models for this machine
@@ -112,7 +115,7 @@ whichllm --top 1 --json

 ![demo](assets/demo.gif)

-## See it
+## 眼见为实

 ```text
 $ whichllm --gpu "RTX 4090"
@@ -122,16 +125,14 @@ $ whichllm --gpu "RTX 4090"
 #3  Qwen/Qwen3-30B-A3B   30.0B  Q5_K_M   score 82.7   102 t/s
 ```

-The 32B model **fits your card fine** — whichllm still ranks the 27B #1,
-because it scores higher on real benchmarks and is a newer generation.
-A size-only "what fits?" tool would hand you the bigger one. That gap is
-the whole point of whichllm. (Note #3: a MoE model at 102 t/s — speed is
-ranked on *active* params, quality on *total*.)
+32B 模型**完全适配你的显卡**——whichllm 仍将 27B 排在第 1 位，
+因为它在真实基准测试中得分更高，且属于更新一代。
+仅按尺寸判断「能跑什么？」的工具会把更大的模型推荐给你。这种差距正是 whichllm 的价值所在。（注 #3：MoE 模型达 102 t/s——速度按*活跃*参数量排名，质量按*总*参数量评估。）

-## What can I run?
+## 我能运行什么？

-Real top picks (snapshot 2026-05 — your results track **live** HuggingFace
-data, this is not a static list):
+真实精选推荐（快照 2026-05——你的结果会跟踪 **实时** HuggingFace
+数据，这不是静态列表）：

 | Hardware | VRAM | Top pick | Speed |
 |---|---|---|---|
@@ -141,68 +142,55 @@ data, this is not a static list):
 | Apple M3 Max | 36 GB | `Qwen3.6-27B` · Q5_K_M · score 89.4 | ~9 t/s |
 | CPU only | — | `gpt-oss-20b` (MoE) · Q4_K_M · score 45.2 | ~6 t/s |

-`whichllm --gpu "<your card>"` simulates any of these before you buy.
-By default, rankings include full-GPU, partial-offload, and CPU-only
-candidates when they are usable. Use `--gpu-only` or `--fit full-gpu` when
-you only want models that fit entirely in GPU VRAM.
-The default table shows memory, estimated generation speed, fit type, and
-published date. Speed is colored by practical usability: under 4 tok/s is red,
-4-10 is yellow, 10-30 is green, and 30+ is bright green. `~` / `?` still mark
-estimate confidence.
+`whichllm --gpu "<your card>"` 可在购买前模拟上述任意配置。
+默认情况下，排名会包含全 GPU、部分卸载和仅 CPU 的候选（在可用时）。若你只想选择完全装入 GPU VRAM 的模型，请使用 `--gpu-only` 或 `--fit full-gpu`。
+默认表格会显示内存、预估生成速度、适配类型和发布日期。速度按实际可用性着色：低于 4 tok/s 为红色，
+4-10 为黄色，10-30 为绿色，30+ 为亮绿色。`~` / `?` 仍会标注
+估算置信度。

-## Why whichllm?
+## 为什么选择 whichllm？

-Fitting a model into your VRAM is the easy part. The hard part is knowing
-**which of the models that fit is actually the best** — and that is what
-whichllm is built to get right.
+把模型塞进 VRAM 并不难。难的是知道**在能跑的模型里，哪一个才是真正最好的**——而这正是
+whichllm 要解决的问题。

- **Evidence-based ranking, not a size heuristic** — The top pick is
-  chosen from merged real benchmarks (LiveBench, Artificial Analysis,
-  Aider, multimodal/vision, Chatbot Arena ELO, Open LLM Leaderboard) —
-  never "the biggest model that happens to fit."
- **Recency-aware** — Stale leaderboards are demoted along each model's
-  lineage, so a 2024 model can't outrank a current-generation one on an
-  outdated score. The benchmark snapshot date is printed under every
-  ranking, so a stale recommendation is self-evident instead of silently
-  trusted.
- **Evidence-graded and guarded** — Every score is tagged
-  `direct` / `variant` / `base` / `interpolated` / `self-reported` and
-  discounted by confidence. Fabricated uploader claims and cross-family
-  inheritance (a small fork borrowing its much larger base's score) are
-  actively rejected.
- **Architecture-aware estimates** — VRAM = weights + GQA KV cache +
-  activation + overhead; speed is bandwidth-bound with per-quant
-  efficiency, per-backend factors, MoE active-vs-total split, and
-  unified-memory vs discrete-PCIe partial-offload modeling.
- **One command, scriptable** — `whichllm` prints the answer; add
-  `--json | jq` for pipelines. No TUI, no keybindings to memorize.
- **Live data** — Models fetched directly from the HuggingFace API, with
-  curated frozen fallbacks for offline or rate-limited use.
+- **基于证据的排名，而非尺寸启发式** —— 首选来自合并的真实基准测试（LiveBench、Artificial Analysis、
+  Aider、多模态/视觉、Chatbot Arena ELO、Open LLM Leaderboard）——
+  绝不是「碰巧能塞进去的最大模型」。
+- **重视时效性** —— 过时的排行榜会沿各模型谱系降权，因此 2024 年的模型不能凭过时分数压过当前一代。
+  每次排名下方都会打印基准快照日期，过时推荐一目了然，而非被默默采信。
+- **证据分级与防护** —— 每个分数都会标注
+  `direct` / `variant` / `base` / `interpolated` / `self-reported`，并
+  按置信度折减。上传者的虚假声明和跨系列继承（小分支借用大得多的基座分数）会被主动拒绝。
+- **架构感知的估算** —— VRAM = 权重 + GQA KV cache +
+  激活 + 开销；速度受带宽限制，并考虑各量化效率、各后端因子、MoE 活跃/总参数拆分，以及统一内存与离散 PCIe 部分卸载建模。
+- **一条命令，可脚本化** —— `whichllm` 直接输出答案；添加
+  `--json | jq` 即可接入流水线。无 TUI，无需记忆快捷键。
+- **实时数据** —— 模型直接从 HuggingFace API 获取，并为离线或限流场景提供精选的冻结回退数据。

-## Features
+## 功能特性

- **Auto-detect hardware** — NVIDIA, AMD, Intel, Apple Silicon, CPU-only
- **Smart ranking** — Scores models by VRAM fit, speed, and benchmark quality
- **One-command chat** — `whichllm run` downloads and starts a chat session instantly
- **Code snippets** — `whichllm snippet` prints ready-to-run Python for any model
- **Live data** — Fetches models directly from HuggingFace (cached for performance)
- **Benchmark-aware** — Integrates real eval scores with confidence-based dampening
- **Task profiles** — Filter by general, coding, vision, or math use cases
- **GPU simulation** — Test with any GPU: `whichllm --gpu "RTX 4090"`
- **Multi-GPU simulation** — Repeat `--gpu`, use commas, or write `2x RTX 4090`
- **Full-GPU filter** — `--gpu-only` / `--fit full-gpu` hides offload candidates
- **Speed-aware filtering** — `--speed usable|fast` hides slow rows by threshold
- **Markdown output** — `--markdown` / `-m` prints pasteable GFM tables
- **Runtime memory budgets** — `--vram-headroom` and `--ram-budget` avoid edge fits
- **Hardware planning** — Reverse lookup: `whichllm plan "llama 3 70b"`
- **Upgrade planning** — Compare your current machine with candidate GPUs
- **JSON output** — Pipe-friendly: `whichllm --json`
+- **自动检测硬件** —— NVIDIA、AMD、Intel、Apple Silicon、仅 CPU
+- **智能排名** —— 按 VRAM 适配、速度和基准质量为模型打分
+- **一条命令聊天** —— `whichllm run` 即时下载并启动聊天会话
+- **代码片段** —— `whichllm snippet` 为任意模型输出可直接运行的 Python 代码
+- **实时数据** —— 直接从 HuggingFace 获取模型（带缓存以提升性能）
+- **基准感知** —— 整合真实评测分数，并按置信度衰减
+- **任务配置** —— 按通用、编程、视觉或数学场景筛选
+- **GPU 模拟** —— 用任意 GPU 测试：`whichllm --gpu "RTX 4090"`
+- **多 GPU 模拟** —— 重复 `--gpu`、使用逗号分隔，或编写 `2x RTX 4090`
+- **全 GPU 筛选** —— `--gpu-only` / `--fit full-gpu` 隐藏卸载候选
+- **速度感知筛选** —— `--speed usable|fast` 按阈值隐藏较慢行
+- **Markdown 输出** —— `--markdown` / `-m` 输出可粘贴的 GFM 表格
+- **运行时内存预算** —— `--vram-headroom` 和 `--ram-budget` 避免临界适配
+- **硬件规划** —— 反向查询：`whichllm plan "llama 3 70b"`
+- **升级规划** —— 将当前机器与候选 GPU 对比
+- **JSON 输出** —— 便于管道处理：`whichllm --json`

-## Run & Snippet
+## 运行与代码片段

-Try any model with a single command. No manual installs needed — whichllm
-creates an isolated environment via `uv`, installs dependencies, downloads the
-model, and starts an interactive chat.
+用一条命令试用任意模型。无需手动安装——whichllm
+通过 `uv` 创建隔离环境，安装依赖，下载
+模型，并启动交互式聊天。

 ![run demo](assets/demo-run.gif)

@@ -217,12 +205,12 @@ whichllm run
 whichllm run "phi 3 mini gguf" --cpu-only
 ```

-Works with **all model formats**:
- **GGUF** — via `llama-cpp-python` (lightweight, fast)
- **AWQ / GPTQ** — via `transformers` + `autoawq` / `auto-gptq`
- **FP16 / BF16** — via `transformers`
+支持**所有模型格式**：
+- **GGUF** — 通过 `llama-cpp-python`（轻量、快速）
+- **AWQ / GPTQ** — 通过 `transformers` + `autoawq` / `auto-gptq`
+- **FP16 / BF16** — 通过 `transformers`

-Get a **copy-paste Python snippet** instead:
+也可直接获取**可复制粘贴的 Python 代码片段**：

 ```bash
 whichllm snippet "qwen 7b"
@@ -245,7 +233,7 @@ output = llm.create_chat_completion(
 print(output["choices"][0]["message"]["content"])
 ```

-## Usage
+## 用法

 ```bash
 # Auto-detect hardware and show best models
@@ -318,26 +306,25 @@ whichllm snippet "qwen 7b"
 whichllm snippet "llama 3 8b gguf" --quant Q5_K_M
 ```

-Markdown output is intended for GitHub issues, READMEs, Slack, Discord, and
-blog posts:
+Markdown 输出适用于 GitHub issues、README、Slack、Discord 和博客文章：

 ```bash
 whichllm --markdown
 whichllm -m --top 5 --gpu "RTX 4090"
 ```

-JSON model rows include `fit_type`, `vram_required_bytes`,
-`vram_available_bytes`, `uses_multi_gpu`, `multi_gpu_effective_vram_bytes`,
-`estimated_tok_per_sec`, `speed_confidence`, `speed_range_tok_per_sec`,
-`speed_notes`, `benchmark_source`, and `benchmark_confidence`. The speed range
-is a planning range, not a live benchmark.
+JSON 模型行包含 `fit_type`、`vram_required_bytes`、
+`vram_available_bytes`、`uses_multi_gpu`、`multi_gpu_effective_vram_bytes`、
+`estimated_tok_per_sec`、`speed_confidence`、`speed_range_tok_per_sec`、
+`speed_notes`、`benchmark_source` 以及 `benchmark_confidence`。速度范围
+是规划参考区间，而非实时基准测试结果。

-## Integrations
+## 集成

 ### Ollama

-Use JSON output to feed scripts that map HuggingFace IDs to your local Ollama
-model names:
+使用 JSON 输出为脚本提供数据，将 HuggingFace ID 映射到本地 Ollama
+模型名称：

 ```bash
 # Pick the top HuggingFace model ID
@@ -347,95 +334,90 @@ whichllm --top 1 --json | jq -r '.models[0].model_id'
 whichllm --profile coding --top 1 --json | jq -r '.models[0].model_id'
 ```

-Ollama model names do not always match HuggingFace repo IDs, so a small mapping
-step is usually needed before `ollama run`.
+Ollama 模型名称并不总与 HuggingFace 仓库 ID 一致，因此在执行 `ollama run` 之前通常需要一步简单映射。

-### Shell alias
+### Shell 别名

-Add to your `.bashrc` / `.zshrc`:
+添加到你的 `.bashrc` / `.zshrc`：

 ```bash
 alias bestllm='whichllm --top 1 --json | jq -r ".models[0].model_id"'
 # Usage: ollama run $(bestllm)
 ```

-## Scoring
+## 评分

-Each model gets a 0-100 score. Benchmark quality and size form the core;
-evidence confidence and runtime fit then scale it, with speed, source
-trust, and popularity as adjustments.
+每个模型获得 0–100 分。基准测试质量与模型规模构成核心；
+证据置信度与运行时适配随后进行缩放，速度、来源可信度与流行度作为调整项。

-| Factor | Effect | Description |
+| 因素 | 作用 | 说明 |
 |--------|--------|-------------|
-| Benchmark quality | core | Merged LiveBench / Artificial Analysis / Aider / Vision / Arena ELO / Open LLM Leaderboard, weighted by source confidence |
-| Model size | up to 35 | `log2`-scaled world-knowledge proxy (MoE uses total params) |
-| Quantization | × penalty | Lower-bit quants discounted multiplicatively |
-| Evidence confidence | ×0.55–1.0 | none / self-reported ×0.55, inherited ×0.78, direct full |
-| Runtime fit | ×0.50–1.0 | partial-offload ×0.72, CPU-only ×0.50 |
-| Speed | -8 to +8 | Usability gate vs a fit-dependent tok/s floor; reported with confidence and range metadata |
-| Source trust | -5 to +5 | Official-org bonus, known-repackager penalty |
-| Popularity | tie-breaker | Downloads/likes; weight shrinks as evidence strengthens |
+| 基准测试质量 | 核心 | 合并 LiveBench / Artificial Analysis / Aider / Vision / Arena ELO / Open LLM Leaderboard，按来源置信度加权 |
+| 模型规模 | 最高 35 | 经 `log2` 缩放的世界知识代理指标（MoE 使用总参数量） |
+| 量化 | × 惩罚 | 低位数量化按乘法折减 |
+| 证据置信度 | ×0.55–1.0 | 无 / 自报 ×0.55，继承 ×0.78，直接完整 |
+| 运行时适配 | ×0.50–1.0 | 部分卸载（partial-offload）×0.72，仅 CPU ×0.50 |
+| 速度 | -8 至 +8 | 可用性门槛对比与适配类型相关的 tok/s 下限；附带置信度与区间元数据报告 |
+| 来源可信度 | -5 至 +5 | 官方机构加分，已知重打包者减分 |
+| 流行度 | 决胜项 | 下载量/点赞数；证据越强权重越小 |

-Score markers:
- **`~`** (yellow) — No direct benchmark; score inherited/interpolated from the model family
- **`!sr`** (bright yellow) — Uploader-reported benchmark only, not independently verified
- **`?`** (red) — No benchmark data available
+评分标记：
+- **`~`**（黄色）— 无直接基准测试；分数从模型家族继承/插值
+- **`!sr`**（亮黄色）— 仅有上传者报告的基准测试，未经独立验证
+- **`?`**（红色）— 无可用基准测试数据

-Speed display:
- **red** — Slow generation speed (`<4 tok/s`)
- **yellow** — Marginal generation speed (`4-10 tok/s`)
- **green** — Usable generation speed (`10-30 tok/s`)
- **bright green** — Fast local generation speed (`>=30 tok/s`)
- **`~`** (yellow) — Estimated tok/s range is available
- **`?`** (red) — Low-confidence speed estimate; backend/runtime sensitivity is high
+速度显示：
+- **red** — 生成速度较慢（`<4 tok/s`）
+- **yellow** — 生成速度勉强可用（`4-10 tok/s`）
+- **green** — 生成速度可用（`10-30 tok/s`）
+- **bright green** — 本地生成速度快（`>=30 tok/s`）
+- **`~`**（黄色）— 提供估算的 tok/s 区间
+- **`?`**（红色）— 低置信度速度估算；对后端/运行时敏感度高

-## Documentation
+## 文档

- [CLI reference](docs/cli.md)
- [How it works](docs/how-it-works.md)
- [Scoring](docs/scoring.md)
- [Hardware detection and simulation](docs/hardware.md)
- [Run and snippet](docs/run-snippet.md)
- [Troubleshooting](docs/troubleshooting.md)
+- [CLI 参考](docs/cli.md)
+- [工作原理](docs/how-it-works.md)
+- [评分](docs/scoring.md)
+- [硬件检测与模拟](docs/hardware.md)
+- [运行与代码片段](docs/run-snippet.md)
+- [故障排除](docs/troubleshooting.md)

-## How it works
+## 工作原理

-### Data pipeline
+### 数据流水线

-1. **Model fetching** — Fetches popular models from HuggingFace API:
-   - Text-generation (downloads + recently updated)
-   - GGUF-filtered (separate query for coverage)
-   - Vision models (`image-text-to-text`) when `--profile vision` or `any`
-2. **Benchmark sources** — *Current tier* (LiveBench, Artificial Analysis
-   Index, Aider) merged live when reachable, plus a curated multimodal /
-   vision index; *frozen tier* (Open LLM Leaderboard v2, Chatbot Arena
-   ELO). Tiers have separate caps and lineage-aware recency demotion so
-   stale leaderboards stop over-rewarding older generations.
-3. **Benchmark evidence** — Five resolution levels, increasingly discounted:
-   - `direct` — Exact model ID match
-   - `variant` — Suffix-stripped or -Instruct variant
-   - `base_model` — Base model from cardData
-   - `line_interp` — Size-aware interpolation within model family
-   - `self_reported` — Uploader-claimed eval (heavily discounted)
+1. **模型获取** — 从 HuggingFace API 获取热门模型：
+   - 文本生成（按下载量 + 最近更新）
+   - GGUF 过滤（单独查询以覆盖）
+   - 视觉模型（`image-text-to-text`），当 `--profile vision` 或 `any` 时
+2. **基准测试来源** — *当前层级*（LiveBench、Artificial Analysis
+   Index、Aider）在可访问时实时合并，外加精选的多模态 /
+   视觉指数；*冻结层级*（Open LLM Leaderboard v2、Chatbot Arena
+   ELO）。各层级设有独立上限，并配合谱系感知的时效性降权，使过时排行榜不再过度奖励旧代模型。
+3. **基准测试证据** — 五个解析层级，折扣递增：
+   - `direct` — 精确模型 ID 匹配
+   - `variant` — 去除后缀或 -Instruct 变体
+   - `base_model` — 来自 cardData 的基础模型
+   - `line_interp` — 模型家族内按规模感知的插值
+   - `self_reported` — 上传者声称的评测（大幅折减）

-   Inheritance is rejected when a model's params diverge more than 2× from
-   its family's dominant member, catching draft / MTP / abliterated forks
-   that share a `family_id` with a much larger base.
-4. **Cache** — normally `~/.cache/whichllm/`, or `$XDG_CACHE_HOME/whichllm/`
-   when `XDG_CACHE_HOME` is set to an absolute path:
+   当模型参数量与其家族主导成员相差超过 2× 时，拒绝继承，
+   以捕获与更大基础模型共享 `family_id` 的 draft / MTP / abliterated 分支。
+4. **缓存** — 通常为 `~/.cache/whichllm/`，或将 `XDG_CACHE_HOME` 设为绝对路径时使用 `$XDG_CACHE_HOME/whichllm/`：
   - `models.json` — 6h TTL
   - `benchmark.json` — 24h TTL

-### Ranking engine
+### 排序引擎

-1. **Hardware detection** — NVIDIA (nvidia-ml-py), AMD (ROCm/dbgpu), Intel, Apple Silicon (Metal), CPU cores, RAM, disk
-2. **VRAM estimation** — Weights + KV cache + activation + framework overhead (~500MB)
-3. **Compatibility** — Full GPU / Partial Offload / CPU-only; compute capability and OS checks
-4. **Speed** — tok/s from GPU memory bandwidth, quantization, backend, fit type, and MoE active parameters
-5. **Scoring** — Benchmark (with confidence dampening), size, quantization penalty, fit type, speed, popularity, source trust (official vs repackager)
-6. **Backend filter** — Apple Silicon and CPU-only restrict to GGUF for stability; Linux+NVIDIA allows AWQ/GPTQ
+1. **硬件检测** — NVIDIA（nvidia-ml-py）、AMD（ROCm/dbgpu）、Intel、Apple Silicon（Metal）、CPU 核心数、RAM、磁盘
+2. **VRAM 估算** — 权重 + KV cache + 激活值 + 框架开销（约 500MB）
+3. **兼容性** — 全 GPU / 部分卸载（Partial Offload）/ 仅 CPU；计算能力与操作系统检查
+4. **速度** — 根据 GPU 内存带宽、量化、后端、适配类型与 MoE 活跃参数量计算 tok/s
+5. **评分** — 基准测试（含置信度衰减）、规模、量化惩罚、适配类型、速度、流行度、来源可信度（官方 vs 重打包者）
+6. **后端过滤** — Apple Silicon 与仅 CPU 为稳定性限制为 GGUF；Linux+NVIDIA 允许 AWQ/GPTQ

-### Project structure
+### 项目结构

 ```
 src/whichllm/
@@ -484,19 +466,18 @@ uv run pytest

 ## Contributing

-Contributions are welcome! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
+欢迎贡献！请参阅 [CONTRIBUTING.md](CONTRIBUTING.md) 了解指南。

 ## Support

-If whichllm helped you find a model or avoid a bad hardware guess,
-sponsoring is appreciated. It helps keep the project maintained: hardware
-reports, packaging, test fixtures, benchmark updates, and support for more
-machines.
+如果 whichllm 帮你找到了合适的模型，或避免了一次糟糕的硬件猜测，
+欢迎赞助。这有助于维持项目：硬件报告、打包、测试夹具（test fixtures）、基准测试更新，
+以及对更多设备的支持。

-whichllm will stay open-source either way. Issues and PRs are always welcome.
+无论是否赞助，whichllm 都会保持开源。Issues 和 PR 始终欢迎。

-Useful? A GitHub star helps other people find it, and I'd genuinely like to
-know what it picked for your rig. Drop it in [Issues](https://github.com/Andyyyy64/whichllm/issues).
+觉得有用？GitHub star 能帮助其他人发现它，我也很想知道
+它为你的配置选了什么。欢迎在 [Issues](https://github.com/Andyyyy64/whichllm/issues).

 ## Star History

@@ -505,8 +486,8 @@ know what it picked for your rig. Drop it in [Issues](https://github.com/Andyyyy
 ## Requirements

 - Python 3.11+
- NVIDIA GPU detection via `nvidia-ml-py` (included by default)
- AMD / Apple Silicon detected automatically
+- 通过 `nvidia-ml-py` 检测 NVIDIA GPU（默认已包含）
+- AMD / Apple Silicon 可自动检测

 ## License