nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
Updated 2 h ago · first seen 11 Sept 2026
model_01M294ZPF4P6M25JJ1HK86T3BD
- Parameters
- 17.8B · 3B active
- T2 · 3 h ago
- Released
- 4 Aug 2026
- T2 · 2 h ago
- License
- other
- T2 · 2 h ago
Specification
- Release date
- 4 Aug 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- License
- other
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Architecture
- NemotronHForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Parameters
- 17.8B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Active parameters
- 3B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Languages
- en, es, fr, de, it, ja
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- File size
- 21.6 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Hugging Face repo
- nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Pipeline tag
- text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Downloads
- 1,303,171
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Likes
- 413
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Last modified
- 2026-09-10T14:41:52+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- License url
- https://openmdw.ai/license/1-1/
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Downloads all time
- 1,389,153
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Model type
- nemotron_h
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Tags
- transformers, safetensors, nemotron_h, text-generation, nvidia, pytorch, nemotron-3.5, en, es, fr, de, it, ja, 8-bit, modelopt
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Weights dtype
- BF16, F32, F8_E4M3, U8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
21
Source tiers
T221
Freshest observation
2 h ago
Conflicts
None
Modalities
Modalities unavailable.
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Unavailable
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
No capability flags have been observed from a source yet — we do not infer them.
- Languages
- en, es, fr, de, it, ja
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
No benchmark results recorded
Current prices
No current prices recorded
Price history
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| Apple M3 Ultra | 4bit | — | 10.8 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 10.8 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 10.8 GB | Yes |
| Apple M2 Ultra | 4bit | — | 10.8 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 10.8 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 10.8 GB | Yes |
| Apple M1 Ultra | 4bit | — | 10.8 GB | Yes |
| Apple M3 Max | 4bit | — | 10.8 GB | Yes |
| Apple M4 Max | 4bit | — | 10.8 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 10.8 GB | Yes |
| Apple M2 Max | 4bit | — | 10.8 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 10.8 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 10.8 GB | Yes |
| Apple M1 Max | 4bit | — | 10.8 GB | Yes |
| Apple M4 Pro | 4bit | — | 10.8 GB | Yes |
| Apple M3 Pro | 4bit | — | 10.8 GB | Yes |
| Apple M1 Pro | 4bit | — | 10.8 GB | Yes |
| Apple M2 Pro | 4bit | — | 10.8 GB | Yes |
| Apple M4 | 4bit | — | 10.8 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 10.8 GB | Yes |
| Apple M2 | 4bit | — | 10.8 GB | Yes |
| Apple M3 | 4bit | — | 10.8 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 10.8 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 10.8 GB | Yes |
| Apple M1 | 4bit | — | 10.8 GB | Yes |
No lineage recorded
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Last modified
Last modifiedlast_modified1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 2026-09-10T14:41:52+00:00 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
New model: nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 (NVIDIA)
huggingface
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 | model_page | T2· Quality secondary | 2 h ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=nvidia&p=0&sort=downloads | listing | T2· Quality secondary | 3 h ago | 2 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.