Updated 19 min ago · first seen 11 Sept 2026
model_01M294ZPG8HB05BERG3MQ5TMVT
- Parameters
- 638M
- T2 · 1 h ago
- Released
- 15 May 2026
- T2 · 21 min ago
- License
- other
- T2 · 21 min ago
Specification
- Release date
- 15 May 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- License
- other
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium
- Architecture
- Nemotron3_5AsrForRNNT
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium
- Parameters
- 638M
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Languages
- en, es, de, fr, it, ar, ja, ko, pt, ru, hi, zh, vi, he, nl, cs, da, pl, no, sv, th, tr, bg, el, et, fi, hr, hu, lt, lv, ro, sk, uk, mt, sl
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium
- Quantization format
- gguf
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium
- File size
- 2.5 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium
- Hugging Face repo
- nvidia/nemotron-3.5-asr-streaming-0.6b
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Pipeline tag
- automatic-speech-recognition
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Downloads
- 722,175
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 19 min agomedium
- Likes
- 1,102
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 19 min agomedium
- Datasets
- nvidia/Granary, multilingual_librispeech, fleurs, mozilla-foundation/common_voice_8_0, voxpopuli, europarl
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium
- Hf inference providers
- deepinfra, fal-ai, together
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium
- Is quantized
- Yes
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium
- Last modified
- 2026-09-10T16:49:07+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Library name
- nemo
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium
- License url
- https://openmdw.ai/license/1-1/
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium
- Downloads all time
- 2,393,449
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 19 min agomedium
- Model type
- nemotron3_5_asr
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium
- Tags
- nemo, safetensors, gguf, nemotron3_5_asr, feature-extraction, transformers, speech-recognition, cache-aware ASR, automatic-speech-recognition, streaming-asr, multilingual, speech, audio, FastConformer, RNNT, Parakeet, ASR, pytorch, NeMo, en, es, de, fr, it, ar, ja, ko, pt, ru, hi
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min agomedium
- Weights dtype
- F32
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min 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
24
Source tiers
T224
Freshest observation
19 min 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, de, fr, it, ar, ja, ko, pt, ru, hi, zh, vi, he, nl, cs, da, pl, no, sv, th, tr, bg, el, et, fi, hr, hu, lt, lv, ro, sk, uk, mt, sl
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 min 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 | — | 0.9 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 0.9 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 0.9 GB | Yes |
| Apple M2 Ultra | 4bit | — | 0.9 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 0.9 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 0.9 GB | Yes |
| Apple M1 Ultra | 4bit | — | 0.9 GB | Yes |
| Apple M3 Max | 4bit | — | 0.9 GB | Yes |
| Apple M4 Max | 4bit | — | 0.9 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 0.9 GB | Yes |
| Apple M2 Max | 4bit | — | 0.9 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 0.9 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 0.9 GB | Yes |
| Apple M1 Max | 4bit | — | 0.9 GB | Yes |
| Apple M4 Pro | 4bit | — | 0.9 GB | Yes |
| Apple M3 Pro | 4bit | — | 0.9 GB | Yes |
| Apple M1 Pro | 4bit | — | 0.9 GB | Yes |
| Apple M2 Pro | 4bit | — | 0.9 GB | Yes |
| Apple M4 | 4bit | — | 0.9 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 0.9 GB | Yes |
| Apple M2 | 4bit | — | 0.9 GB | Yes |
| Apple M3 | 4bit | — | 0.9 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 0.9 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 0.9 GB | Yes |
| Apple M1 | 4bit | — | 0.9 GB | Yes |
No lineage recorded
Papers 2
- arXiv:2312.17279Active35
- arXiv:2305.05084Active35
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 · Likes
Likesmetric.likes1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 1,102 | → 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: nemotron-3.5-asr-streaming-0.6b (NVIDIA)
huggingface
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b | model_page | T2· Quality secondary | 19 min ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=nvidia&p=0&sort=downloads | listing | T2· Quality secondary | 1 h ago | 2 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.