Nemotron 3.5 Lightning
NVIDIAReleased Aug 11, 2026Open weights · NVIDIA Open Model Licensenemotron-3.5-lightning
- Reasoning
- yes
- Knowledge cutoff
- June 2024
- Context
- 262K tokens
- Max output
- 128k tokens
- Input
- text
- API features
- tools, structured outputs, JSON mode, seed, logprobs
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from NVIDIA · cutoff: aiknowledgecutoff.com
Free right now
- Free OpenRouter, served by Nvidia · no end date · 20 req/min, 50 req/day, 1,000 req/day with $10 of credits
Checked Oct 23 · every free model on Deals
The cheapest host, Io Net, serves a weights precision we can't read (host terms). Cheapest at the maker's precision and context: DeepInfra, $0.22 blended. Weights and context per host
Run it yourself
open weights, NVIDIA Open Model License · fits 6 of the 6 workstations in our guideSelf-host guide ›- Parameters
- 30B
- 3B active per token (MoE)
- Memory needed
- 18 GB
- in INT4 · 36 GB in INT8
- Smallest cloud setup
- RTX 3090
- 24 GB · $0.17/h, about $124 a month
- Worth it above
- 686M tokens
- a month, against the cheapest API at $0.18 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 18 GB | RTX 3090 · $0.17/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 36 GB | A100 · $1.19/h | near-lossless |
| FP16 (full) | 72 GB | A100 · $1.19/h | reference quality |
At home: in INT4 it fits a RTX 5090 (32 GB) + host PC (plus a host PC), about $3,500 once, or $0.1332/h over 3 years, electricity aside; it pays for itself after about 19B tokens against the cheapest API.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| Io Netprecision not read: host terms · 256K ctx · 128K out−33% | $0.0469 | $0.13 | $0.0235 | 84 | 0.51 s | 97.9% | Oct 23 |
| DeepInfrabf16 · 256K ctx · 32K out | $0.06 | $0.16 | $0.03 | — | — | 100% | Oct 23 |
| CoreWeavebf16 · 256K ctx | $0.07 | $0.20 | $0.04 | 167 | 0.32 s | 100% | Oct 23 |
| Phalaprecision not read: host terms · 256K ctx | $0.07 | $0.20 | $0.04 | — | — | 99.6% | Oct 10 |
4 of 4 providers · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · −N%: a discount off the host's list price · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| Io Net | not read: host terms | 256K | 128K | yes | yes | yes |
| DeepInfra | bf16 | 256K | 32K | yes | yes | yes |
| CoreWeave | bf16 | 256K | not checked yet | yes | yes | yes |
| Phala | not read: host terms | 256K | not read: host terms | yes | yes | yes |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
Nemotron 3.5 Lightning spec sheet, field by field, with sources
Nemotron 3.5 Lightning spec sheetmaker-declared
What NVIDIA declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- 262,144 tokens
- Parameters
- 31,577,937,344≈ 31.6B
- Active experts
- 6 of 128 active per token
- Weight precision
- BF16
- License
- NVIDIA Open Model License — open weights, conditionalcuratedScope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- not published by the maker≈ June 2024 third-party estimate — not the maker's figurecurated
- Modalities
- text
- Max output (official)
- to verify
- Release date
- to verify≈ August 11, 2026 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
Also declared in the weights
- Architecture class
- NemotronHForCausalLM
- Layers
- 52
- Vocabulary
- 131,072 tokens
- Weights first published
- August 1, 2026
- Weights last updated
- August 24, 2026
- Languages declared
- English · Spanish · French · German · Italian · Japanese
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · config.json @ a9904d2 · read 2026-10-08 · 6 of 10 fields published by the maker
| Date | Provider | Input | Output | Change |
|---|---|---|---|---|
| Oct 9 | Io Net | $0.049 → $0.0469 | $0.14 → $0.13 | −4% |
| Oct 6 | Io Net | $0.0595 → $0.049 | $0.17 → $0.14 | −18% |
| Sep 30 | Io Net | $0.063 → $0.0595 | $0.18 → $0.17 | −6% |
| Sep 29 | DeepInfra | $0.08 → $0.06 | $0.20 → $0.16 | −21% |
| Sep 28 | Io Net | $0.0665 → $0.063 | $0.19 → $0.18 | −5% |
| Sep 15 | CoreWeave | $0.10 → $0.07 | $0.25 → $0.20 | −23% |
Every published change of input or output price, newest first · change on input + output · full series: pricing-history.csv.
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| Io Net | $0.11 | $0.44 | $0.32 |
| DeepInfra | $0.14 | $0.56 | $0.40 |
| CoreWeave | $0.17 | $0.66 | $0.48 |
| Phala | $0.17 | $0.66 | $0.48 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other NVIDIA models · all its models, hosts and history ›
- Nemotron 3.5 Super VL7 providers · from $0.50
- Nemotron 3 Nano 30B A3B4 providers · from $0.25
- Nemotron 3 Super4 providers · from $0.48
- Nemotron 3 Ultra3 providers · from $2.70
- Nemotron 3.5 Content Safety1 provider · from $0.40
- Nemotron 3 Nano Omni 30B A3B Reasoning0 provider · from —