NVIDIA: Nemotron 3.5 Lightning.
Nemotron 3.5 Lightning is NVIDIA's 30B mixture-of-experts text model, 3B active, with up to 1M-token context; the BF16 weights are meant for customization.
1× Nvidia RTX A4500 · $0.19/hr.
Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.
Cheapest hosted endpoints.
Variants in the Nemotron family.
NVIDIA: Nemotron 3 Ultra
A 550B open-weights text model (55B active) for complex agents, long-context ...
NVIDIA: Nemotron 3.5 Content Safety
Nemotron 3.5 Content Safety is NVIDIA's 4B moderation model that labels promp...
NVIDIA: Nemotron 3.5 Super VL
A 120B open-weights vision-language model (12B active) that reads text, image...
NVIDIA: Nemotron 3 Nano 30B A3B
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest com...
NVIDIA: Nemotron 3 Super
A 120B open-weights text model (12B active) for agent workflows, tool use and...
NVIDIA: Nemotron Nano 9B V2
NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scrat...
Nemotron-3-Nano-Omni-30B-A3B-Reasoning
Nemotron 3 Nano Omni is an open multimodal model built on a hybrid Mixture-of...
Cheapest hardware per quantisation.
Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/hr refreshed hourly from each provider's API.
| Quantisation | Cheapest GPU config | Total VRAM | Live $/hr | tokens/sec | |
|---|---|---|---|---|---|
|
FP16
FP16 — half precision (default)
|
80 GB | $1.09/hr | — | Compare → | |
|
FP8
FP8 — 8-bit float (Hopper / Blackwell)
|
40 GB | $1.39/hr | — | Compare → | |
|
INT4
INT4 — 4-bit integer (~4× VRAM saving)
|
20 GB | $0.19/hr | — | Compare → |
What it costs per month across providers.
Estimate your monthly bill for NVIDIA: Nemotron 3.5 Lightning across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
Cheapest provider on the left.
Total monthly cost — input + output tokens combined.
Bill breakdown.
Rent the GPU instead of paying per token.
For an open-weights model like NVIDIA: Nemotron 3.5 Lightning, you can rent a GPU and serve inference yourself. The math: cheapest GPU rental × 730 hours/month + your electricity rate × power draw.
Assumes the GPU runs 24/7 at ~85% utilisation. If your traffic is bursty, you'll pay less for the API and probably more for the GPU (idle hours still cost rental). The breakeven analysis lives on the Self-host vs API breakeven tool.
About NVIDIA: Nemotron 3.5 Lightning.
Nemotron 3.5 Lightning is an NVIDIA text model with open weights, training data and recipes, under the OpenMDW licence and ready for commercial use. It is a hybrid of Mamba-2, mixture-of-experts and attention layers, with 30B parameters in total and 3B active. Context reaches 1M tokens, or 256K on a single H100 80GB. Reasoning can be switched on or off. This full-precision BF16 release is meant for customization and post-training. NVIDIA points deployers to the separate NVFP4 release for faster inference.