LLM gatewaysAgent frameworks

AirLLM

lyogavin/airllm

Run a 70B model on a single 4GB GPU — no quantization, no distillation, no pruning.

Repository
Stars
30.4k
Forks
3.2k
Open issues
135
Language
Jupyter Notebook
Licence
Apache-2.0
Created
2023-06-12
Last push
2026-08-09
Effort to adopt

Engineering project

Weeks, not days. Treat it as infrastructure with an owner and a budget.

01

What it actually does

AirLLM attacks the memory problem in inference by streaming layers rather than holding the whole model in GPU memory. The headline claim is a 70B model running on a single 4GB card without quantization, distillation, or pruning — meaning you are running the actual model, not a degraded copy.

The numbers scale further than that. 405B Llama 3.1 on 8GB. DeepSeek-V3 at 671B on roughly 12GB. Kimi K3 at 2.8 trillion parameters on under 4GB, because sparse mixture-of-experts models stream one expert at a time instead of a whole layer.

The trade-off is the obvious one and worth stating plainly: streaming weights costs you latency. This is a throughput-and-cost play, not a way to serve low-latency interactive traffic.

It is Apache 2.0, has been maintained since 2023, and supports macOS as well as Linux.

02

Who it's for

  • 01

    Teams who want to run large open models without renting large GPUs

  • 02

    Anyone doing batch inference where latency does not matter but cost does

  • 03

    Companies with data residency rules that make hosted APIs a non-starter

  • 04

    Researchers evaluating frontier open models on modest hardware

EngineeringDataFinanceSaaSFintechHealthtechAny industry
03

Where it earns its keep

  • Batch-processing a document backlog overnight on hardware you already own
  • Evaluating whether a large open model is good enough before committing to GPU spend
  • Keeping sensitive data entirely on-premise while still using a capable model
  • Running periodic classification or extraction jobs without a per-token API bill
  • Prototyping against a frontier-size model on a developer workstation
04

Use it, or skip it

Reach for it when

  • Throughput matters and latency genuinely does not
  • Data cannot leave your infrastructure
  • GPU budget is the binding constraint, not wall-clock time
  • You want the full model rather than a quantized approximation

Skip it when

  • You are serving interactive users. Layer streaming makes responses slow
  • A quantized model would be good enough — it will be far faster
  • Your volume is low. A hosted API will be cheaper than the engineering time
  • You have no one to operate GPU infrastructure
05

10 automations

  1. 01Operations

    Overnight document classification

    Batch-process the day's uploaded documents on local hardware while nobody is waiting, with results ready by morning.

  2. 02Operations

    On-premise PII extraction

    Extract structured fields from sensitive records without any data leaving your own network.

  3. 03Engineering

    Model evaluation harness

    Run your eval suite against several large open models locally before deciding which to pay to host.

  4. 04Support

    Support ticket backlog analysis

    Process a year of tickets in batch to find recurring themes, without a five-figure API bill.

  5. 05Marketing

    Bulk content scoring

    Score a large content library against quality or brand criteria overnight and rank what needs rewriting.

  6. 06Sales

    CRM enrichment sweep

    Enrich and normalise a full CRM export locally, rather than paying per record to an external service.

  7. 07Finance

    Compliance review pass

    Run a first-pass review of contracts or policies on infrastructure your compliance team already approved.

  8. 08Finance

    Cost comparison model

    Benchmark local batch inference against your current API spend to decide where the crossover point is.

  9. 09Engineering

    Air-gapped inference

    Serve a capable model inside a fully disconnected environment where hosted APIs are impossible.

  10. 10Operations

    Nightly summarisation job

    Summarise all internal documents changed that day and publish a digest before the team logs on.

Want one of these running by Friday?

LimeDock builds these as real workflows inside your stack — deployed to your cloud, wired into your Slack and CRM, with the code in your repo. You pay a build fee and your own API keys, nothing else.

Book a workflow call
07

Source

Repository stats were read from the GitHub API and reflect the last time we refreshed this entry. The editorial breakdown above is LimeDock’s own analysis — we are not affiliated with lyogavin.

https://github.com/lyogavin/airllm