Compare AI models

Specifications
Parameters
4B35B
Context window
256k256k
API pricing
Input price
—$0.375International (Singapore)
Output price
—$2.25
Cheapest input
—$0.05Darkbloom
Cheapest output
—$0.70Darkbloom
—$45.00Darkbloom · fp4
Benchmarks
GPQA Diamond
53.2%86%
Overview
CompanyNVIDIAQwen
Release dateMar 16 2026Apr 16 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.6 leads Nemotron 3 Nano 4B on 1 of the 1 benchmark they both report (GPQA Diamond). Only Qwen3.6 has a verified first-party price for an available API: $0.375 per million input tokens and $2.25 per million output tokens. No currently available pay-as-you-go API rate is tracked for Nemotron 3 Nano 4B. The listed Qwen3.6 rates use the “International (Singapore)” pricing scope. Nemotron 3 Nano 4B shipped 31 days before Qwen3.6, so benchmark comparisons should account for the intervening progress.

Nemotron 3 Nano 4B has 4B parameters, while Qwen3.6 has 35B. Context windows are 256k (Nemotron 3 Nano 4B) vs 256k (Qwen3.6).

On GPQA Diamond, Qwen3.6 leads at 86% vs Nemotron 3 Nano 4B at 53.2%.