LogoLMSpeed
  • Home
  • Free
  • Providers
  • Docs
LogoLMSpeed
LogoLMSpeed

The best API speed test tool

GitHubGitHubTwitterX (Twitter)Email
Product
  • Features
  • Pricing
  • FAQ
Leaderboard
  • Overview
  • Speed Ranking
  • Latency Ranking
  • Health Ranking
Models
  • All Models
  • GPT
  • Claude
  • Gemini
  • DeepSeek
  • Llama
  • Qwen
Free Models
  • All Free Models
  • Free GPT
  • Free Claude
  • Free Gemini
  • Free DeepSeek
  • Free Llama
  • Free Qwen
Resources
  • Speed Test
  • Provider Directory
  • Documentation
Legal
  • Cookie Policy
  • Privacy Policy
  • Terms of Service
© 2026 LMSpeed All Rights Reserved.Made by Nexmoe with ❤️
首页交流 QQ 群:1034193296,欢迎中转站站长加入讨论 AI 最热话题、newapi、openclaw 等,获取最新测速动态与反馈支持。
Ollama logo

Ollama

Ollama provides a platform to run and integrate open-source AI models locally or in the cloud.

ChatGLMGLM-5ChatGLMGLM-5.1MinimaxMiniMax-M2.7

Ollama offers 3 LLM API models.

Speed benchmark average: 54 tok/s.

Ollama interface preview
Avg Speed53.98 tok/s
Latency20.77 s
Total Tests35
Models3
Updated4/11/2026
Created At3/23/2026
Website

API Endpoints

  • ollama.com

Recent Test Records

TimeModelSpeedLatency
Apr 13, 02:24 PM
ChatGLMglm-5.1:cloud
40.89 tok/s
42.51s
Apr 13, 02:20 PM
ChatGLMglm-5.1:cloud
49.79 tok/s
25.82s
Apr 13, 02:12 PM
ChatGLMglm-5.1:cloud
94.03 tok/s
9.61s
Apr 7, 11:24 AM
Minimaxminimax-m2.7
34.06 tok/s
5.97s
Apr 7, 08:55 AM
Minimaxminimax-m2.7
31.79 tok/s
18.11s
Apr 7, 08:11 AM
ChatGLMglm-5
51.14 tok/s
34.23s
Mar 23, 09:10 AM
ChatGLMglm-5
76.14 tok/s
9.13s

Leaderboard Rankings

Speed
78.3 tokens/s#33/100
OverviewPerformance3PricingTests35HealthEmbed