SwarmandBee

DiabeticDaily-4B

Deploy Dedicated
Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

License: apache-2.0

Beat-base — proven

Held-out perplexity vs base Qwen3.5-4B (text never trained on):

Table
held-out lossperplexity
Base Qwen3.5-4B1.50624.510
DiabeticDaily-4B0.89822.455
Δ−0.608 (+40.4% better)

Verdict: BEAT BASE ✅. A 4B that models diabetic/medical language ~40% better than base — and at Q4 it's ~2.6GB, running at usable speed on a Jetson with PHI never leaving the box.

How it was cooked

  • Base: Qwen/Qwen3.5-4B (Apache-2.0). Data: the same deeded OpenDiabetic corpus as the 27B/9B.
  • Recipe: LoRA r32/α16 on attn+mlp, LR 2e-5 (small-model tier), 0.7ep, early-stop. Merged bf16.

Run it on a Jetson (Q4 GGUF, ollama) — see the -GGUF companion repo

bash
ollama create diabetic-daily -f Modelfile   # FROM diabeticedge-4b-q4_k_m.gguf
ollama run diabetic-daily "What's a good diabetic breakfast?"

This is the brain behind the LocalDiabetic edge node — sovereign, private, free.

The ladder: 🐝 27B anchor (+57%) → 🏠 9B home (+40.7%) → 🛏️ 4B edge (+40.4%)

⚠️ Not medical advice — diabetic lifestyle/education/organization only. Not a diagnosis. Emergencies → 911.

© 2026 Swarm and Bee LLC · opendiabetic.com · Apache-2.0 · We slow cook the truth. 🐝

Model provider

SwarmandBee

Model tree

Base

Qwen/Qwen3.5-4B

Quantized

this model

Modalities

Input

Video, Text, Image

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Model card

Explore FriendliAI today

Get startedTalk to an engineer