tiyuvta/Qwen3.8-Flash-Next-NVFP4
Image-Text-to-Text • 117B • Updated • 108
AI & ML interests
Tiyuvta.ai hosts open LLMs with an OpenAI-compatible API tuned for low latency and agent performance. It offers full tool calling, instant API keys, and pay-per-use pricing with no subscriptions or minimums and is targeted at customer support, automation, agent-based products and always-on agents.
Recent Activity
Organization Card
Tiyuvta.ai
Open LLMs behind an OpenAI-compatible API, tuned for low latency and agent performance.
Tiyuvta.ai gives builders full tool calling, instant API keys, and pay-per-use pricing — no subscriptions, no minimums. Built for customer support, automation, agent-based products, and always-on agents.
Links
- 🌐 Website: inference.tiyuvta.ai
- 🐦 X (Twitter): @tiyuvta
- 💼 LinkedIn: tiyuvta-ai
What we offer
- Open-weight LLMs served behind a familiar OpenAI-compatible API
- Full tool/function calling for agent workloads
- Instant API keys — no approval wait
- Pay-per-use pricing, no subscriptions or minimums
- Tuned for low latency and always-on agents
Explore our models below.
models 11
tiyuvta/Hy3-NVFP4
Text Generation • 154B • Updated • 497 • 1
tiyuvta/GLM-5.3-Flash-NVFP4
Text Generation • 164B • Updated • 348 • 1
tiyuvta/DeepSeek-V4-Flash-0731-NVFP4
Text Generation • 304B • Updated • 123
tiyuvta/memra-bench
32.8k • Updated • 1.53k • 3
tiyuvta/Qwen3.8-27B-DSpark-Agentic
Text Generation • 1B • Updated • 1.08k • 4
tiyuvta/Qwen3.8-27B-DFlash2-memra
Text Generation • 2B • Updated • 1.12k • 2
tiyuvta/Ornith-1.5-9B-NVFP4-MTP-GGUF
Text Generation • 32.8k • Updated • 1.1k • 1
tiyuvta/Qwen3.8-27B-NVFP4-MTP-GGUF
Text Generation • 32.8k • Updated • 11.1k • 14
tiyuvta/Ornith-1.5-35B-A3B-NVFP4-MTP-GGUF
Text Generation • 67.1M • Updated • 7.24k • 4
datasets 0
None public yet