Skip to content

Summary

Simulate how fast a local LLM runs on a given GPU or Mac before you buy the hardware.

Screenshots

Description

llmspeed lets you feel the speed of a local language model before spending money on hardware. Pick a device and a model and it simulates the output in real time, using tokens per second and time-to-first-token figures drawn from verified benchmarks.

The hardware list covers NVIDIA RTX and datacenter GPUs, AMD Radeon and Ryzen AI Max systems, Intel Arc, Apple Silicon Macs, DGX Spark and CPU-only setups. The model list includes current open-weight families such as Qwen, Gemma, GLM, DeepSeek, GPT-OSS and Llama. Estimates assume a short prompt on a single device, and measured numbers come from community benchmarks.

It is free to use and helpful for anyone choosing a GPU, a Mac or a mini PC for running models locally.

Reviews

No reviews yet — sign in to write the first one

Similar App Suggestions

See all llmspeed alternatives

App: Unsloth

Unsloth AI

Featured

Open-source desktop app to run, serve and fine-tune text, image, video and audio models entirely on your own machine.

Coding & DevelopmentFree

Inference and training platform for open models: serverless per-token APIs, dedicated GPU deployments, and managed fine-tuning with SFT, DPO and RFT.

Coding & DevelopmentPaid

NVIDIA GPU cloud for training and inference: self-serve on-demand instances billed by the minute, 1-Click Clusters, and large private superclusters.

Coding & DevelopmentPaid

GPU cloud for AI developers: on-demand GPU pods, serverless GPU endpoints that scale to zero, and multi-node clusters, billed by the second.

Coding & DevelopmentPaid

A generative media platform tuned for speed — image, video, and audio models served with very low latency.

Image & DesignFreemium