🧪 Model Benchmark Tester - HF CPU Space

Input repo and model file name to benchmark GGUF or Transformers models. Adjust generation hyperparameters as needed.

Model Type

Repo ID (e.g., TheBloke/Mistral-7B-Instruct-v0.1-GGUF)

Model File Name (only for GGUF)

Test Prompt

Max New Tokens

1 16384

n_ctx (GGUF only)

256 32768

Max Tokens (GGUF only)

1 16384

Temperature

0 1.5

Top-p

0 1

Top-k

0 100

Model Output

Inference Time

CPU Usage

RAM Usage

Disk Usage (downloaded size)