Overview

Identity

Identity block not returned by the API for this entity.

Openness

Openness not classified yet — no sourced evidence to place this model in the ontology.

Key facts

Release date: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium
Model card: huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Architecture

Architecture: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium
Model type: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium
Parameters: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
Weights dtype: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium
File size: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium
Library name: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium
Pipeline tag: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium
Hugging Face repo: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Capabilities

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: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Hardware fit37

Estimated

37 of 37 device × quantization combinations fit.

Run locally: your machine →

Estimated hardware fit
Hardware	Quantization	Device memory	Est. memory	Fits
Apple M3 Ultra	4bit	—	0.9 GB est.	Yes
Mac Studio (Apple M5 Ultra)	4bit	—	0.9 GB est.	Yes
Apple M2 Ultra	4bit	—	0.9 GB est.	Yes
Apple M1 Ultra	4bit	—	0.9 GB est.	Yes
Apple M3 Max	4bit	—	0.9 GB est.	Yes
Apple M4 Max	4bit	—	0.9 GB est.	Yes
Mac Studio (Apple M5 Max)	4bit	—	0.9 GB est.	Yes
MacBook Pro (Apple M5 Max)	4bit	—	0.9 GB est.	Yes
Apple M2 Max	4bit	—	0.9 GB est.	Yes
Apple M1 Max	4bit	—	0.9 GB est.	Yes
Apple M4 Pro	4bit	—	0.9 GB est.	Yes
Mac mini (Apple M5 Pro)	4bit	—	0.9 GB est.	Yes
MacBook Pro (Apple M5 Pro)	4bit	—	0.9 GB est.	Yes
Apple M3 Pro	4bit	—	0.9 GB est.	Yes
Apple M1 Pro	4bit	—	0.9 GB est.	Yes
Apple M2 Pro	4bit	—	0.9 GB est.	Yes
Apple M4	4bit	—	0.9 GB est.	Yes
iMac (Apple M4)	4bit	—	0.9 GB est.	Yes
Mac mini (Apple M6)	4bit	—	0.9 GB est.	Yes
MacBook Air (Apple M5)	4bit	—	0.9 GB est.	Yes
MacBook Pro (Apple M5)	4bit	—	0.9 GB est.	Yes
Apple M2	4bit	—	0.9 GB est.	Yes
Apple M3	4bit	—	0.9 GB est.	Yes
Apple M1	4bit	—	0.9 GB est.	Yes
NVIDIA GeForce RTX 3090	4bit	24 GB	0.9 GB est.	Yes
NVIDIA GeForce RTX 4090	4bit	24 GB	0.9 GB est.	Yes
NVIDIA GeForce RTX 5090	4bit	32 GB	0.9 GB est.	Yes
NVIDIA A100 80GB	4bit	80 GB	0.9 GB est.	Yes
NVIDIA H100 SXM	4bit	80 GB	0.9 GB est.	Yes
NVIDIA H100 NVL	4bit	94 GB	0.9 GB est.	Yes
NVIDIA DGX Spark	4bit	128 GB	0.9 GB est.	Yes
NVIDIA H200	4bit	141 GB	0.9 GB est.	Yes
NVIDIA H200 NVL	4bit	141 GB	0.9 GB est.	Yes
NVIDIA B200	4bit	180 GB	0.9 GB est.	Yes
AMD Instinct MI300X	4bit	192 GB	0.9 GB est.	Yes
AMD Instinct MI325X	4bit	256 GB	0.9 GB est.	Yes
NVIDIA DGX B200	4bit	1,440 GB	0.9 GB est.	Yes

Assumptions (6)

Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead.
bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
KV cache approximated at 0.5 GB per 8 192 tokens of context, independent of architecture (GQA/MLA models need less).
A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).

Papers2

arXiv:2312.17279Active
35
arXiv:2305.05084Active
35

Datasets6

europarlActive
35
nvidia/GranaryActive
35
mozilla-foundation/common_voice_8_0Active
35
fleursActive
35
multilingual_librispeechActive
35
voxpopuliActive
35

Timeline1

Full timeline →

11 Sept 2026
New modelModelnemotron-3.5-asr-streaming-0.6bNVIDIA
New model: nemotron-3.5-asr-streaming-0.6b (NVIDIA)
huggingface
huggingface.co

Change history25

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.

Viewing AI Atlas as of 12 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Attributes as of 12 Sept 2026 26 claims in force

Release date: 15 May 2026
Openness: open-weights
License: Other
Architecture: Nemotron3_5AsrForRNNT
Parameters: 638M
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
Quantization format: gguf
File size: 2.5 GB
Hugging Face repo: nvidia/nemotron-3.5-asr-streaming-0.6b
Pipeline tag: automatic-speech-recognition
Model card: huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b
Downloads: 722,175
Likes: 1,102
Datasets: nvidia/Granary, multilingual_librispeech, fleurs, mozilla-foundation/common_voice_8_0, voxpopuli, europarl
Gated: No
Hf inference providers: deepinfra, fal-ai, together
Is quantized: Yes
Last modified: 2026-09-10T16:49:07+00:00
Library name: nemo
License name: openmdw-1.1
License url: https://openmdw.ai/license/1-1/
Downloads all time: 2,393,449
Model type: nemotron3_5_asr
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
Weights available: Yes
Weights dtype: F32

25 claims · 25 properties

Release daterelease_date1

Claim history for Release date
Value	Valid from → to	Status	Source	Confidence	Extractor
15 May 2026	11 Sept 2026 21:54 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Opennessopenness1

Claim history for Openness
Value	Valid from → to	Status	Source	Confidence	Extractor
open-weights	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Licenselicense1

Claim history for License
Value	Valid from → to	Status	Source	Confidence	Extractor
other	11 Sept 2026 21:54 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Architecturearchitecture1

Claim history for Architecture
Value	Valid from → to	Status	Source	Confidence	Extractor
Nemotron3_5AsrForRNNT	11 Sept 2026 21:54 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Parametersparameter_count1

Claim history for Parameters
Value	Valid from → to	Status	Source	Confidence	Extractor
638M	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Languageslanguages1

Claim history for Languages
Value	Valid from → to	Status	Source	Confidence	Extractor
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	11 Sept 2026 21:54 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Quantization formatquant_format1

Claim history for Quantization format
Value	Valid from → to	Status	Source	Confidence	Extractor
gguf	11 Sept 2026 21:54 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

File sizefile_size_gb1

Claim history for File size
Value	Valid from → to	Status	Source	Confidence	Extractor
2.5 GB	11 Sept 2026 21:54 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
Value	Valid from → to	Status	Source	Confidence	Extractor
nvidia/nemotron-3.5-asr-streaming-0.6b	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Pipeline tagpipeline_tag1

Claim history for Pipeline tag
Value	Valid from → to	Status	Source	Confidence	Extractor
automatic-speech-recognition	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Model cardmodel_card_url1

Claim history for Model card
Value	Valid from → to	Status	Source	Confidence	Extractor
https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Downloadsmetric.downloads1

Claim history for Downloads
Value	Valid from → to	Status	Source	Confidence	Extractor
722,175	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Likesmetric.likes1

Claim history for Likes
Value	Valid from → to	Status	Source	Confidence	Extractor
1,102	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Datasetsdatasets1

Claim history for Datasets
Value	Valid from → to	Status	Source	Confidence	Extractor
nvidia/Granary, multilingual_librispeech, fleurs, mozilla-foundation/common_voice_8_0, voxpopuli, europarl	11 Sept 2026 21:54 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Gatedgated1

Claim history for Gated
Value	Valid from → to	Status	Source	Confidence	Extractor
No	11 Sept 2026 21:54 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Hf inference providershf_inference_providers1

Claim history for Hf inference providers
Value	Valid from → to	Status	Source	Confidence	Extractor
deepinfra, fal-ai, together	11 Sept 2026 21:54 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Is quantizedis_quantized1

Claim history for Is quantized
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 21:54 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Last modifiedlast_modified1

Claim history for Last modified
Value	Valid from → to	Status	Source	Confidence	Extractor
2026-09-10T16:49:07+00:00	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Library namelibrary_name1

Claim history for Library name
Value	Valid from → to	Status	Source	Confidence	Extractor
nemo	11 Sept 2026 21:54 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

License namelicense_name1

Claim history for License name
Value	Valid from → to	Status	Source	Confidence	Extractor
openmdw-1.1	11 Sept 2026 22:28 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

License urllicense_url1

Claim history for License url
Value	Valid from → to	Status	Source	Confidence	Extractor
https://openmdw.ai/license/1-1/	11 Sept 2026 21:54 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Downloads all timemetric.downloads_all_time1

Claim history for Downloads all time
Value	Valid from → to	Status	Source	Confidence	Extractor
2,393,449	11 Sept 2026 21:54 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Model typemodel_type1

Claim history for Model type
Value	Valid from → to	Status	Source	Confidence	Extractor
nemotron3_5_asr	11 Sept 2026 21:54 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Tagstags1

Claim history for Tags
Value	Valid from → to	Status	Source	Confidence	Extractor
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	11 Sept 2026 21:54 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Weights dtypeweights_dtype1

Claim history for Weights dtype
Value	Valid from → to	Status	Source	Confidence	Extractor
F32	11 Sept 2026 21:54 UTC → 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 →

Provenance

Attributed facts

25

Source tiers

T225

Freshest observation

10 h ago

Conflicts

None

Source documents 3

Source documents
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	10 h ago	3
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/models?author=nvidia&p=0&sort=downloads	listing	T2· Quality secondary	10 h ago	3
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b/raw/main/README.md	model_card	T2· Quality secondary	11 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (53/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →