Skip to content
Back to the index

benchrig

PyPIInfrastructure

PulseGate's liveness check found it on 20 Sep 2026; it is registered on PyPI and has been in the index since 20 Sep 2026. How this is checked

benchrig is an open-source benchmarking and profiling rig for local large language models. It supports Ollama, Microsoft Foundry Local, and ONNX Runtime GenAI, with keywords indicating CUDA and Apple Silicon support.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI

Overview

6 features

Purpose: Benchmarking and profiling local language models consistently across different inference runtimes and hardware.

Inferred · not functionally tested

Audience: developers and ML engineers evaluating local LLM performance

Inferred · not functionally tested

Functions: analytics, monitoring

Inferred · not functionally tested

Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org. These links do not verify the individual claims.

benchrig sits in PulseGate's LLM evaluation & benchmarks category. Inferred · not functionally tested: It focuses on benchmarking and profiling local language models consistently across different inference runtimes and hardware. Inferred · not functionally tested: It is built as an open-source project for developers and ML engineers evaluating local LLM performance. Basis unknown · not verified: benchrig is open source under the MIT license. Basis unknown · not verified: benchrig is available on the command line, and it can be self-hosted.

benchrig first shipped in 2026. Inferred · not functionally tested: Key capabilities include LLM Benchmarking, Performance Profiling, and Ollama Support.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • LLM Benchmarking
  • Performance Profiling
  • Ollama Support
  • Foundry Local Support
  • ONNX Runtime Support
  • CUDA Support

Topics: Inferred · not functionally tested

Tags
llm-benchmarkinglocal-inferenceollamaonnx-runtime
AI capabilities
Text
Inference: Local

JSON profile · Text profile · Access guide

Built with & integrations

AI providers
local_oss
Runs on
CLISelf-hosted

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceFree tier

Indexing history

2

What PulseGate has recorded for this listing

  1. Indexed23 Sep · 15:43 UTC
    benchrig seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open
  2. Indexed20 Sep · 08:39 UTC
    benchrig seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about benchrig

What does benchrig do?
Inferred · not functionally tested: Benchrig focuses on benchmarking and profiling local language models consistently across different inference runtimes and hardware. It is catalogued under LLM evaluation & benchmarks on PulseGate.
Who is benchrig for?
Inferred · not functionally tested: benchrig is an open-source project built for developers and ML engineers evaluating local LLM performance.
Is benchrig free?
Basis unknown · not verified: Yes — benchrig is open source under the MIT license and free to use.
What platforms does benchrig run on?
Basis unknown · not verified: benchrig runs on the command line. It can also be self-hosted.
Is benchrig still active?
PulseGate's liveness check found it on 20 Sep 2026.
What are alternatives to benchrig?
Similar projects tracked by PulseGate include bench-my-llm, llm-benchmark-runner, and porchbench.bench-my-llmllm-benchmark-runnerporchbench
How long has benchrig been around?
benchrig first shipped in 2026.
Is benchrig open source?
Basis unknown · not verified: Yes — benchrig is open source under the MIT license.

Similar projects

Closest matches by what these projects do