# Jittor/JittorLLMs

计图大模型推理库，具有高性能、配置要求低、中文支持好、可移植等特点

Repository: https://github.com/Jittor/JittorLLMs
Canonical: https://ross.abutalabs.com/products/jittorllms
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-02-22T15:02:56+00:00

## Health v2 (maintenance only)
Score: 34/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 8, release rhythm 35, longevity 89
- inputs: {"age_days": 1249, "days_push": 557, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2413, forks 187 (observed 2026-08-28T04:06:44.505510+00:00)

## What it is
JittorLLMs is a large language model inference library built on the Jittor deep learning framework, supporting models like ChatGLM, LLaMA/LLaMA2, ChatRWKV, PanGu, MOSS, and Atom7B. It dramatically lowers hardware requirements—running LLMs on machines with as little as 2GB RAM and no GPU—while offering fast loading via zero-copy technology and cross-platform portability.

## Use cases
- run a large language model locally without a GPU
- deploy ChatGLM or LLaMA on a low-memory laptop
- serve an LLM behind a REST API
- chat with Chinese LLMs like ChatGLM and PanGu in a browser
- migrate LLM inference across heterogeneous hardware without code changes
- demo an LLM with a gradio web interface

## When to choose
- you have limited RAM or no GPU and want local LLM inference
- you need good Chinese-language model support
- you want a one-command CLI, web, or API deployment of multiple open LLMs
- you need portable inference across different compute devices

## When to avoid
- you need the broadest model ecosystem or fastest GPU throughput of mainstream frameworks like vLLM or llama.cpp
- you require production-grade scaling or multi-GPU serving
- you need fine-tuning or training features rather than inference

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, chatbot, machine-learning, cli, http-server
- domain: large-language-models, artificial-intelligence, chatbots
- platform: windows, python, cli
- tags: low-resource-inference, cpu-inference, chatglm, llama, chatrwkv, pangu, jittor, chinese-llm, gradio-web-demo, natural-language-processing, linux, macos

## Member repositories
- Jittor/JittorLLMs (main) score 34

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:44.505510+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:33:13.537980+00:00, confidence not recorded.
  - readme: https://github.com/Jittor/JittorLLMs (fetched 2026-08-28T04:06:44.505510+00:00, sha b8e041dbb18b)
- Data as of 2026-08-30T08:39:29.467469+00:00.