cd /news/large-language-models/flow-a-compact-data-pipeline-languag… · home topics large-language-models article
[ARTICLE · art-57515] src=github.com ↗ pub= topic=large-language-models verified=true sentiment=↑ positive

Flow – a compact data pipeline language that cuts LLM token usage by 33%

A new open-source data pipeline language called Flow reduces LLM token usage by an average of 33% compared to Python by stripping away human-oriented boilerplate. Developed by Pinku, Flow uses single-character operators and transpiles to Python, with validated results on fine-tuned models like phi-2 and Qwen 3B Coder v2 running on consumer GPUs.

read5 min views1 publishedJul 13, 2026
Flow – a compact data pipeline language that cuts LLM token usage by 33%
Image: source

A compact, AI-optimized data transformation language for LLMs

~33% token reduction vs Python — validated with fine-tuned models on consumer GPUs

git clone https://github.com/pinku/Flow.git && cd Flow
python3 flow.py "1..10 | f:_>5 | m:_*2"

No dependencies. No setup. Just Python 3.8+.

LLMs are trained on verbose human-oriented languages, but that verbosity burns tokens without adding value for AI processing:

Problem Impact
Keywords like function , const , return
Every one costs tokens
Verbose variable names for human readability No benefit for LLMs
Syntactic sugar optimized for humans Wasted context window

Flow strips away the human-oriented boilerplate, keeping only what the LLM needs to express the transformation. The result: 33% fewer tokens on average, tested and verified with real models.

Python (24 tokens) Flow (13 tokens) — 45% fewer
result = [x * 2 for x in range(1, 11) if x > 5]
`1..10 f:_>5

More examples in the Operator Reference.

Feature Description
Minimal Syntax
Single-character operators: f: (filter), m: (map), g: (group), a: (aggregate), etc.
Python Compatible
Transpiles to clean, readable Python
LLM Optimized
Designed for minimal token usage without sacrificing expressiveness
JSON Native
Built-in JSON parsing and serialization
Batch Processing
Windowing and batching for large datasets
Type Safety
Type casting and validation
Zero Dependencies
Pure Python — no pip install required
git clone https://github.com/pinku/Flow.git
cd Flow
python3 flow.py --help
python3 flow.py "1..10 | f:_>5 | m:_*2"

python3 flow.py "[{name:'Alice',age:30},{name:'Bob',age:25}] | g:_.age>=30 | a:len(v)"

python3 flow.py "S:data.json"  # Save to JSON
python3 flow.py "J"             # Parse JSON input
python3 flow.py
python
from flow import flow_run, flow_transpile

result = flow_run("1..10 | f:_>5 | m:_*2")
print(result)  # [12, 14, 16, 18, 20]

code = flow_transpile("1..10 | f:_>5 | m:_*2")
print(code)  # [_*2 for _ in range(1, 11) if _>5]
Operator Name Example
f:
Filter `data f:_.age > 18`
m:
Map `data m:_.name.upper()`
g:
Group `data g:_.category`
a:
Aggregate `data g:_.cat
s:
Sort `data s:-_.age`
t:
Take `data t:10`
d:
Drop `data d:2`
u
Unique `data u`
r
Reverse `data r`
b:
Batch `data b:32`
w:
Window `data w:3`
i:
Split `data i:'\n'`
o:
Join `data o:','`
T:
Type cast `data T:int`
J
Parse JSON `data J`
S:
Save JSON `data S:output.json`
x
Flatten `nested x`
&
AND filter `data f:_.a>0 & _.b<10`
` `
OR filter `data f:_.a>0

Full interactive report: benchmark_report.html

Task Python Tokens Flow Tokens Savings
Filter + Map 22 13 41%
Group + Aggregate 25 14 44%
Sort + Take 20 14 30%
JSON Parse 15 4 73%
Batch Processing 35 8 77%

Average token saving: 33%

Flow has been validated with fine-tuned models on consumer hardware:

Model Parameters VRAM Training Time Accuracy
phi-2 2.7B ~5.4 GB ~20 min 100%
Qwen 3B Coder v2 3.7B ~6.0 GB ~5 min 100%

Both models were fine-tuned using QLoRA (4-bit quantization) on an RTX 4060.

Flow includes training scripts for fine-tuning small language models:

pip install transformers peft bitsandbytes trl

python3 generate_dataset.py

python3 train_qlora.py

python3 train_qwen_flow.py

Requirements:

  • NVIDIA GPU with 8GB+ VRAM (RTX 4060 tested)
  • CUDA 12.x
  • Python 3.8+

Flow includes a Hermes skill for seamless integration:

cp -r .hermes/skills/flow-tool ~/.hermes/skills/

/hermes run flow-tool "1..10 | f:_>5 | m:_*2"
Flow/
├── flow.py                  # Main implementation (transpiler + runtime)
├── data/
│   └── flow_dataset.json    # Training dataset (600 examples)
├── models/                  # Fine-tuned LoRA adapters (not in repo)
│   ├── flow-lora/           # phi-2 adapter
│   └── qwen3b-flow-lora-v2/ # Qwen 3B adapter
├── benchmark_report.html    # Visual benchmark report
├── train_qlora.py           # phi-2 training script
├── train_qwen_flow.py       # Qwen 3B training script
└── generate_dataset.py      # Dataset generation script

Hermes Agent— LLM agent platform; Flow is used as a tool skillllama.cpp— Local LLM inference; models trained on Flow data run here

MIT License — free for any use.

This project explores the hypothesis that purpose-built languages for LLMs can achieve significant efficiency gains compared to traditional programming languages. The key findings:

Token efficiency is real: Flow achieves 33% token reduction on average** Small models can learn**: 2.7-3.7B parameter models achieve 100% accuracy after fine-tuning** Hardware accessible**: QLoRA enables training on consumer GPUs (RTX 4060)

For the full analysis and methodology, see benchmark_report.html.

── more in #large-language-models 4 stories · sorted by recency
── more on @flow 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/flow-a-compact-data-…] indexed:0 read:5min 2026-07-13 ·