IPv4 Beta LM Studio appears to expose an LM Studio API endpoint at ipv4-beta.kxcym.top:11434. The server currently returns LM Studio authentication errors rather than a public landing page.
IPv4 Beta LM Studio offers 14 LLM API models.
Speed benchmark average: 141 tok/s.
ipv4-beta.kxcym.top:11434ipv4-beta.kxcym.toppv4-beta.kxcym.top| Model | Speed | Latency | Tests |
|---|---|---|---|
387.70 tok/s | 1.63s | 5 | |
qwen3.5-0.8b | 354.52 tok/s | 0.82s | 10 |
243.42 tok/s | 2.62s | 5 | |
Qwen/qwen3.5-0.8b | 241.83 tok/s | 0.59s | 5 |
206.16 tok/s | 6.63s | 5 | |
huihui-ai/Huihui-Qwen3.5-0.8B-abliterated | 181.27 tok/s | 2.80s | 10 |
huihui_ai/qwen3.5-abliterated:2B-fp16 | 174.08 tok/s | 9.88s | 5 |
huihui-qwen3.5-35b-a3b-abliterated-i1 | 142.42 tok/s | 1.18s | 5 |
huihui_ai/qwen3.5-abliterated:9b | 92.02 tok/s | 13.99s | 5 |
HauhauCS/qwen3.5-instruct | 56.10 tok/s | 1.15s | 5 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| 03/29/2026, 11:37 | Qwen/qwen3.5-0.8b | 241.83 tok/s | 0.59s |
| 03/28/2026, 15:36 | huihui-ai/Huihui-Qwen3.5-0.8B-abliterated | 198.32 tok/s | 0.57s |
| 03/28/2026, 15:34 | huihui-ai/Huihui-Qwen3.5-0.8B-abliterated | 164.22 tok/s | 5.03s |
| 03/27/2026, 08:39 | qwen3.5-0.8b | 345.41 tok/s | 0.75s |
| 03/27/2026, 08:34 | qwen3.5-0.8b | 363.63 tok/s | 0.90s |
APDSM provides a unified API gateway for accessing multiple large language models and AI services through standardized endpoints.
3 shared models
A unified API gateway for large language models, offering access to multiple providers through standardized endpoints.
2 shared models
毫秒API provides a stable, high-bandwidth API forwarding service for OpenAI-compatible models, including GPT, Claude, and Midjourney, with global server deployment and transparent pricing.
2 shared modelsProvides API access to a wide range of AI models including text, image, and video generation from multiple providers.
2 shared models
柏拉图AI (api.bltcy.cn) is a multi-dimensional API integration platform providing access to over 600 AI models, serving as an alternate endpoint.
2 shared models
天絮 API provides an AI model relay service with multiple access points and stable connectivity.
2 shared models