Small language models (1B–3B): what they're good for after fine-tuning

Presenting to a room
Presenting to a room

Originally published at https://pranjulrathour.scult.in/blog/small-language-models-1b-3b-use-cases. That copy is the canonical version and gets updates first.

A 1.7B-parameter model will not write your thesis. It will, after fine-tuning, classify ten thousand support tickets an hour on a CPU, for free, without sending customer data anywhere. FineTune Studio is built around small models because that trade is the one most teams actually need.

Where small models win

  • Classification and routing — intent detection, ticket triage, deciding which expensive model a request deserves. Fine-tuned small models are consistent and cheap here.
  • Structured extraction — pulling fields from a known document type into a schema. Pair with validation and you have a deterministic pipeline.
  • Format enforcement — producing strict JSON, a house style, or a fixed template every time.
  • Privacy-bound tasks — anything that must not leave the server or the device.
  • Latency-bound tasks — sub-second responses on modest hardware.

Where they still lose

  • Open-ended reasoning across long contexts.
  • Knowledge-heavy questions — use retrieval, not parameters, for facts (see RAG vs fine-tuning).
  • Tasks with few examples; small models need the data to learn the behaviour.

A pattern that works in production

A fine-tuned small model in front, doing the cheap, frequent, narrow work; a frontier API behind it for the hard cases it flags. Costs drop, latency drops, and the expensive model is used where it matters. Multi-provider fallback, as in RAG.NextUpgrad, keeps the expensive path reliable.

How to prove it

Train on your data, then run the base model, the tuned model and the frontier API on the same held-out set and score them with the same rubric. When the tuned 1.7B model matches the API on your task at a fraction of the cost, you have a result worth putting in a portfolio — and a talking point for any GenAI interview.

Pranjul Rathour
Pranjul Rathour
Presenting KrishGyan, farming advice in your voice and language
Presenting KrishGyan, farming advice in your voice and language
From my carousels
1,211 Prompts, Every One Stamped
1,211 Prompts, Every One Stamped, slide 11,211 Prompts, Every One Stamped, slide 2
1,211 Prompts, Every One Stamped, slide 31,211 Prompts, Every One Stamped, slide 4
Full carousel on Instagram and LinkedIn.
Pranjul Rathour
Pranjul Rathour
GenAI engineer, Kanpur · 3x first-prize hackathon winner · campus mentor
I ship production RAG pipelines, fine-tune LLMs and build agentic AI products end to end. I lead engineering at SCULT INDIA for a 14-member team and have mentored 200+ students through TechVerse Enclave.
Open to: GenAI roles, hackathon judging, mentorship sessions and guest talks at colleges.
On stage, at hackathons and on campus
At an Integral Startup Foundation hackathon
At an Integral Startup Foundation hackathon
Pranjul Rathour
Pranjul Rathour
Walking a room through the products he has shipped
Walking a room through the products he has shipped

Comments

Post a Comment

Popular posts from this blog

Forming a hackathon team: roles, skills and the mistake most teams make

Image
At an Integral Startup Foundation hackathon Originally published at https://pranjulrathour.scult.in/blog/hackathon-team-roles-and-formation . That copy is the canonical version and gets updates first. Team TechVerse — Raman Shukla, Saksham Gupta and me — won three first prizes in 2025 not because we were the strongest coders in the room, but because we had stopped overlapping. When I mentor teams before a hackathon, formation is the first thing I fix. In a packed college auditorium The four roles Builder — owns the core feature and the demo path. Usually backend or the AI piece. Interface — owns what the judge sees: the front end, the flow, the seeded data. Storyteller — owns the problem statement, the pitch, the slides and the Q&A plan; also does user research in hour one. Integrator — keeps the pieces working together, manages the repo, runs the demo rehearsals. In a team of three, the builder or interface person takes this. The mistake Five friends who all write R...
Read more

Hello from Kanpur: what I build, and what I'll write about here

Image
On the mic Originally published at https://dev.to/pranjulrathour/hello-from-kanpur-what-i-build-and-what-ill-write-about-here-f2j . That copy is the canonical version and gets updates first. I'm Pranjul Rathour, a GenAI engineer from Kanpur, India. This is the first post on this blog, so here is who is writing, what I have actually shipped, and what you can expect if you follow along. What I build Between February and July 2026, at Next Upgrad Web Solutions, I designed, built and shipped five production AI applications end to end, alone, and deployed all of them with Docker, CI and observability: RAG.NextUpgrad : a retrieval-augmented generation service with hybrid dense plus BM25 retrieval, cross-encoder reranking, streaming cited answers, and a confidence gate that refuses to call the model when the evidence is weak. It runs in about 220 MB of memory, inside a free 512 MB instance. FineTune Studio : fine-tune open models with QLoRA in a browser. Upload a dataset, validate ...
Read more

I built 15 free tools, 1,211 prompts and a 50,000-skill library — here's what's inside tools.scult.in

Image
Carousel · 12 slides I built every part of tools.scult.in myself — 15 browser tools, 1,211 version-stamped prompts, a 50,000+ agent-skills library, a public MCP server, and 40 retro photo prompts where I'm the face in every example. All of it free. No signup, no ads, no upload step. Swipe through for what's inside and why I built it this way. Link in the last slide. Slide 1 of 12 Slide 2 of 12 Slide 3 of 12 Slide 4 of 12 Slide 5 of 12 Slide 6 of 12 Slide 7 of 12 Slide 8 of 12 Slide 9 of 12 Slide 10 of 12 Slide 11 of 12 Slide 12 of 12 Pranjul Rathour GenAI engineer, Kanpur · 3x first-prize hackathon winner · campus mentor I ship production RAG pipelines, fine-tune LLMs and build agentic AI products end to end. I lead engineering at SCULT INDIA for a 14-member team and have mentored 200+ students through TechVerse Enclave. Open to: GenAI roles, hackathon judging, mentorship sessions and guest talks at colleges. Email: pranjulrathour41@gmail.com Portfolio & ...
Read more