全新 Mac 主机部署与全维度评测 Qwen3.8-27B-Uncensored 完整指南

xcode-select --install

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

echo 'eval "$(/opt/homebrew/bin/brew shellenv)"' >> ~/.zprofile
eval "$(/opt/homebrew/bin/brew shellenv)"

brew install [email protected] git git-lfs curl jq

mkdir -p ~/omlx/scripts \
         ~/omlx-models \
         ~/.omlx/logs \
         ~/.omlx/cache \
         ~/.omlx/backups

python3.13 -m venv ~/omlx/.venv
source ~/omlx/.venv/bin/activate

pip install --upgrade pip wheel setuptools
pip install omlx huggingface_hub

# 验证安装
omlx --version

export HF_ENDPOINT=https://hf-mirror.com

~/omlx/.venv/bin/hf download pyros-vault/Qwen3.8-27B-Uncensored-oQ4e-fp16-mtp \
  --local-dir ~/omlx-models/Qwen3.8-27B-Uncensored-oQ4e-fp16-mtp

ls -lh ~/omlx-models/Qwen3.8-27B-Uncensored-oQ4e-fp16-mtp

cat << 'EOF' > ~/.omlx/model_settings.json
{
  "version": 1,
  "models": {
    "Qwen3.8-27B-Uncensored-oQ4e-fp16-mtp": {
      "max_context_window": 65536,
      "max_tokens": 16384,
      "temperature": 0.0,
      "top_p": 0.95,
      "top_k": 20,
      "repetition_penalty": 1.0,
      "min_p": 0.0,
      "presence_penalty": 0.0,
      "force_sampling": false,
      "chat_template_kwargs": {
        "enable_thinking": false,
        "preserve_thinking": false,
        "reasoning_effort": "low"
      },
      "model_type_override": "vlm",
      "enable_thinking": false,
      "preserve_thinking": false,
      "thinking_budget_enabled": false,
      "guided_grammar_enabled": false,
      "turboquant_kv_enabled": false,
      "turboquant_kv_bits": 4.0,
      "turboquant_skip_last": true,
      "mtp_enabled": true,
      "is_pinned": true,
      "is_default": true,
      "display_name": "Qwen3.8 27B Uncensored oQ4e FP16-MTP",
      "description": "Qwen3.8-27B Uncensored oQ4e FP16 MTP accelerated model"
    }
  }
}
EOF

CURRENT_USER=$(whoami)

cat << EOF > ~/.omlx/settings.json
{
  "version": "1.0",
  "server": {
    "host": "127.0.0.1",
    "port": 8000,
    "log_level": "info",
    "cors_origins": ["*"],
    "server_aliases": ["localhost", "127.0.0.1"],
    "sse_keepalive_mode": "chunk",
    "auto_start_on_launch": true,
    "burst_decode_mode": "aggressive",
    "preserve_mid_system_cache": true,
    "gpu_keep_warm_interval": 300.0
  },
  "model": {
    "model_dirs": ["/Users/${CURRENT_USER}/omlx-models"],
    "model_dir": "/Users/${CURRENT_USER}/omlx-models"
  },
  "memory": {
    "prefill_memory_guard": true,
    "memory_guard_tier": "aggressive",
    "memory_guard_custom_ceiling_gb": 0.0,
    "soft_threshold": 0.90,
    "hard_threshold": 0.95,
    "prefill_safe_zone_ratio": 0.8,
    "prefill_min_chunk_tokens": 32
  },
  "scheduler": {
    "max_concurrent_requests": 1,
    "chunked_prefill": true,
    "prefill_priority": "context",
    "decode_fairness": true
  },
  "cache": {
    "enabled": true,
    "hot_cache_only": false,
    "gdn_ssd_split_enabled": true,
    "ssd_cache_dir": "/Users/${CURRENT_USER}/.omlx/cache",
    "ssd_cache_max_size": "92GB",
    "hot_cache_max_size": "16GB"
  },
  "auth": {
    "api_key": "omlx-local-key",
    "skip_api_key_verification": true,
    "allow_unauthenticated_inference": false
  },
  "sampling": {
    "max_context_window": 65536,
    "max_tokens": 16384,
    "temperature": 0.0,
    "top_p": 0.95,
    "top_k": 20,
    "repetition_penalty": 1.0
  }
}
EOF

CURRENT_USER=$(whoami)

cat << EOF > ~/Library/LaunchAgents/com.user.omlx.server.plist
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
    <key>Label</key>
    <string>com.user.omlx.server</string>
    <key>ProgramArguments</key>
    <array>
        <string>/Users/${CURRENT_USER}/omlx/.venv/bin/omlx</string>
        <string>serve</string>
        <string>--model-dir</string>
        <string>/Users/${CURRENT_USER}/omlx-models</string>
        <string>--port</string>
        <string>8000</string>
        <string>--max-concurrent-requests</string>
        <string>1</string>
    </array>
    <key>RunAtLoad</key>
    <true/>
    <key>KeepAlive</key>
    <dict>
        <key>SuccessfulExit</key>
        <false/>
        <key>Crashed</key>
        <true/>
    </dict>
    <key>WorkingDirectory</key>
    <string>/Users/${CURRENT_USER}/omlx</string>
    <key>StandardOutPath</key>
    <string>/Users/${CURRENT_USER}/.omlx/logs/server.log</string>
    <key>StandardErrorPath</key>
    <string>/Users/${CURRENT_USER}/.omlx/logs/server.log</string>
</dict>
</plist>
EOF

launchctl bootstrap "gui/$(id -u)" ~/Library/LaunchAgents/com.user.omlx.server.plist

{
  "providers": {
    "omlx-local": {
      "baseUrl": "http://127.0.0.1:8000/v1",
      "api": "openai-completions",
      "apiKey": "omlx-local-key",
      "compat": {
        "supportsDeveloperRole": false,
        "supportsReasoningEffort": false,
        "maxTokensField": "max_tokens"
      },
      "models": [
        {
          "id": "Qwen3.8-27B-Uncensored-oQ4e-fp16-mtp",
          "name": "Qwen 3.8 27B Uncensored (oMLX Local 8000)",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 65536,
          "maxTokens": 16384,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        }
      ]
    }
  }
}

{
  "defaultProvider": "omlx-local",
  "defaultModel": "Qwen3.8-27B-Uncensored-oQ4e-fp16-mtp"
}

~/omlx/.venv/bin/omlx launch pi --model Qwen3.8-27B-Uncensored-oQ4e-fp16-mtp

cat << 'EOF' > ~/Desktop/启动Qwen38工作站.command
#!/bin/bash
USER_ID=$(id -u)
PLIST="$HOME/Library/LaunchAgents/com.user.omlx.server.plist"

echo "================================================="
echo "   正在启动/激活 Qwen3.8-27B 本地推理服务..."
echo "================================================="

launchctl kickstart -k "gui/${USER_ID}/com.user.omlx.server" 2>/dev/null || \
  launchctl bootstrap "gui/${USER_ID}" "$PLIST"

echo "⏳ 正在等待 8000 端口上线..."
for i in {1..30}; do
  if curl -s http://127.0.0.1:8000/v1/models >/dev/null 2>&1; then
    echo "✅ 服务已就绪！(http://127.0.0.1:8000)"
    osascript -e 'display notification "Qwen3.8-27B 本地工作站已就绪！" with title "oMLX 推理底座"'
    break
  fi
  sleep 1
done

echo ""
echo "最近运行日志："
tail -n 10 "$HOME/.omlx/logs/server.log"
echo "================================================="
read -n 1 -s -r -p "按任意键退出窗口..."
EOF

chmod +x ~/Desktop/启动Qwen38工作站.command

# 使用 PI CLI 执行工程级多文件审计任务
pi --model omlx-local/Qwen3.8-27B-Uncensored-oQ4e-fp16-mtp \
   -p "请检查当前目录结构，列出所有 python 脚本，并用表格汇报各自的文件大小与主要函数数量"

# 构造包含 32K tokens 虚构文档，在 50% 深度处埋入标记短语
# 验证模型能否在首轮准确回答：“文档中提到的秘密口令是什么？”