framebench
Estimated game fps for any GPU or Apple Silicon chip, with the limiter and tweaks.
MCP serverInference & Hosting
What we know
| MCP server | Yessource, checked 2026-11-13 |
|---|
Alternatives
None listed.
Is your tool an alternative to framebench? Sponsor this spot for 30 days, marked Sponsored.
Integrations
None listed.
Built on
None listed.
Related tools
- AWS BedrockFully managed foundation model service on AWS — Claude, Llama, Titan, and more
- Azure OpenAIOpenAI models with Microsoft Azure security, compliance, and SLAs
- BasetenML model deployment platform — deploy any model as a production API in minutes
- Cerebras ChatUltra-fast AI inference chat — run Llama and other open models at 2,000+ tokens/second on Cerebras WSE hardware
- Fireworks AIUltra-fast serverless inference for open-source LLMs — Llama, Mixtral, and SDXL at speed
- GroqUltra-fast LLM inference API — run Llama, Mixtral, and Gemma at 500+ tokens/second on custom LPU hardware
- LoRAXMulti-LoRA inference server — serve hundreds of fine-tuned adapters on a single GPU
- OpenRouterSingle API for 100+ LLMs — compare models, route to the best, pay per token
- PortkeyAI gateway for LLM routing, fallbacks, caching, and observability — production-ready in minutes
- PredibaseManaged fine-tuning and LoRA serving — production-grade custom LLM deployment
For the team behind framebench
Growth plan: from $399 a month
SEO, AI search (how ChatGPT, Perplexity and Google describe framebench), UX, CRO and support from one account manager, with a monthly report. Includes a Featured launch on db.fyi. Starts with a free audit.
Founding offer: $299 a month for your first 3 months, plus a free case study.
Listed 2026-11-13 · updated 2026-11-13