Local Ai
Curious about ollama kimi-k2.6:cloud speed? 3 test runs: > 77.9 tok/s, TTFT 979ms > 114.3 tok/s, TTFT 788ms > 86.3 tok/s, TTFT 1117ms For co…
Curious about ollama kimi-k2.6:cloud speed? 3 test runs: > 77.9 tok/s, TTFT 979ms > 114.3 tok/s, TTFT 788ms > 86.3 tok/s, TTFT 1117ms For comparison, OpenRouter stats: > Parasail: 14 tok/s > Moonshot
Curious about ollama kimi-k2.6:cloud speed? 3 test runs: > 77.9 tok/s, TTFT 979ms > 114.3 tok/s, TTFT 788ms > 86.3 tok/s, TTFT 1117ms For comparison, OpenRouter stats: > Parasail: 14 tok/s > Moonshot AI: 27 tok/s > NovitaAI: 27 tok/s > Cloudflare: 71 tok/s Obvious caveat: cloud speeds fluctuate with load. Just sharing numbers for the curious. Media @stevibe is ollama cloud not slow for you? Maybe i just got cooked as part of the a/b users, but it takes a LOT of minutes to get a response
Related
- Kimi Kimi 。 Kimi Kimi Kimi Kimi Kimi Kimi ollama run kimi-k2.6:cloud
- Model page https://ollama.com/library/kimi-k2.6 More integrations https://docs.ollama.com/integrations
- How much more useage do you get from a $20 pro plan when using cloud models? Or OpenRouter better??
- ollama launch hermes Ollama 0.21 includes supports Hermes Agent, the self-improving AI agent built by @NousResearch.
Source: Ollama (X) | 2026-04-21