Model
NVIDIA Nemotron 3.5 Lightning 30B A3B
Recorded as suitable for chat, rag, coding, agentic.
- Source
- Model registry API
- Verified
- 19 Sep 2026
- Confidence
- High
01What this is
- Author
- nvidia
- Family
- Nemotron 3.5
- Task
- text-generation
- Hugging Face
- nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
- OpenRouter
- nvidia/nemotron-3.5-lightning
- Also known as
- Nemotron 3.5 Lightning, nemotron-3.5-lightning, nemotron lightning
02Registry facts
- LicenceFACT
other
- FreshRetrieved 19 Sep 2026
- ParametersFACT
31.6B
- FreshRetrieved 19 Sep 2026
- Context lengthFACT
not returned by the registry
- Evidence not verified
- Downloads (30 days)FACT
576,090
- FreshRetrieved 19 Sep 2026
- LikesFACT
215
- FreshRetrieved 19 Sep 2026
- GatedFACT
no
- FreshRetrieved 19 Sep 2026
Model
- downloadsFACT
576090
- Verification may be outdatedRetrieved 19 Sep 2026
- gatedFACT
false
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · CoreWeaveFACT
262144
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · PhalaFACT
262144
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · DarkbloomFACT
262144
- Verification may be outdatedRetrieved 19 Sep 2026
- likesFACT
215
- Verification may be outdatedRetrieved 19 Sep 2026
- model licenseFACT
other
- Verification may be outdatedRetrieved 19 Sep 2026
- parameter countFACT
31577937344
- Verification may be outdatedRetrieved 19 Sep 2026
Pricing
- hosted price completion per m · CoreWeaveFACT
0.2000
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · PhalaFACT
0.2000
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · DarkbloomFACT
0.1800
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · CoreWeaveFACT
0.0700
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · PhalaFACT
0.0700
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · DarkbloomFACT
0.0400
- AgeingRetrieved 19 Sep 2026
Other
- last modifiedFACT
2026-08-24T23:46:27.000Z
- Verification may be outdatedRetrieved 19 Sep 2026
- libraryFACT
transformers
- AgeingRetrieved 19 Sep 2026
03VRAM by quantisation
Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: 31.6B parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).
| Quantisation | Weights | Total |
|---|---|---|
| bf16bf16 is two bytes per weight, the same arithmetic as fp16. | 63.16 GB | 82.51 GB |
| fp8 | 31.58 GB | 46.19 GB |
| int4 | 15.79 GB | 28.04 GB |
| q4_k_mSized as 4-bit weights. Q4_K_M averages nearer 4.5 bits in practice, so read this as a floor. | 15.79 GB | 28.04 GB |
What this estimate assumes
- Weights: 31.6B parameters × 2 bytes per parameter (fp16) = 63.16 GB.
- No model configuration was supplied, so the KV cache uses the size heuristic for this band: 0.262 MB per token, from Qwen2.5-32B-Instruct (64 × 8 × 128).
- KV cache: 0.262 MB per token × 8,192 tokens of context × 4 concurrent requests = 8.59 GB, sized for every user holding a full context at once.
- Overhead: 15% of weights plus KV cache for the runtime, activations and memory fragmentation = 10.76 GB.
- GB means 10⁹ bytes, matching how GPU memory is advertised.
- KV cache held at fp16 (2 bytes per element); quantising weights does not by itself quantise the cache.
- Peak figure, not average: prefix caching and paged attention usually keep real usage lower, while speculative decoding, CUDA graphs and a second resident model push it higher.
- "Concurrent" counts requests generated at the same instant, not people: 4 simultaneous requests is the worst case this estimate is built on — measure yours before buying.
04Hardware profiles
No hardware profile was sized for this answer.
05Hosted providers
- Prompt (per million tokens, USD)FACT
0.04
Source: openrouter
- FreshRetrieved 19 Sep 2026
- Completion (per million tokens, USD)FACT
0.18
- FreshRetrieved 19 Sep 2026
| Provider | Context |
|---|---|
| Darkbloom | 262,144 |
| Phala | 262,144 |
| CoreWeave | 262,144 |
| DeepInfra | 262,144 |
06Deployment stacks
No published deployment stack names this model yet.
07Evidence
- 01–09Tier 4official repository / model cardOpenRouter
OpenRouter endpoints — nvidia/nemotron-3.5-lightning
https://openrouter.ai/api/v1/models/nvidia/nemotron-3.5-lightning/endpoints
AgeingRetrieved 19 Sep 2026sha256:4071124c80ad9 records · · · · · · · ·
- 10–16Tier 4official repository / model cardHugging Face Hub
Hugging Face model card data — nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
https://huggingface.co/api/models/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Verification may be outdatedRetrieved 19 Sep 2026sha256:89c55f5de1307 records · · · · · ·
Improve this page
Sign in to contribute
From the field
0 deployments · 0 questions
Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.