nemotron-3.5-asr-streaming-0.6b
NVIDIAfamily · Nemotron 3.5huggingface.co/nvidia/nemotron-3.5-asr-streaming
Updated 4 h ago · first seen 11 Sept 2026
model_01M294ZPG8HB05BERG3MQ5TMVT
Overview
Identity
- Canonical model
- Yesidentity confidence: highOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
- Official checkpoints
- official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
- Artifacts
- None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
- Provider deployments
- None recorded
- API aliases
- NoneIdentifiers under which providers and evaluators refer to this model.
- Folded evaluation variants
- 0Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.
Openness
Open weights— weights downloadable under Other; 7 dimensions unknown.
Weights downloadable under a permissive or Creative Commons licence allowing commercial use; code or data may be missing.
Weights
Yes
Inference code
—
Training code
—
Training data
—
Dataset
—
Commercial use
—
Redistribution
—
Derivatives
—
Licence: Other (unclassified licence) (unknown · stated as “other”)
dimensions marked null are unknown, not false
Key facts
- Release date
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium
Architecture
- Architecture
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium
- Model type
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium
- Parameters
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium
- Weights dtype
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium
- File size
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium
- Library name
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium
- Pipeline tag
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium
- Hugging Face repo
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 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 13 h agomedium
Hardware fit37
Assumptions (7)
- Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded).
- bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
- KV cache: 2 × layers × kv_heads × head_dim × 2 bytes × context × batch when the architecture is known; otherwise 0.5 GB per 8 192 tokens (× batch), 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).
- Multi-GPU: device memories are summed; interconnect bandwidth, tensor-parallel replication and pipeline bubbles are not modelled.
Versions & Artifacts0
Version history
Licensefirst observation only
11 Sept 2026current
Opennessfirst observation only
11 Sept 2026current
Parametersfirst observation only
11 Sept 2026current
Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.
Artifacts 0
No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.
Papers2
- arXiv:2312.17279Active35
- arXiv:2305.05084Active35
Datasets6
- europarlActive35
- fleursActive35
- voxpopuliActive35
- nvidia/GranaryActive35
- multilingual_librispeechActive35
Change history26
Viewing AI Atlas as of 11 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.
Back to today →Attributes as of 11 Sept 2026 25 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
- 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 dtype
- F32
Release daterelease_date1
Opennessopenness1
Licenselicense1
Architecturearchitecture1
Parametersparameter_count1
Languageslanguages1
Quantization formatquant_format1
File sizefile_size_gb1
Hugging Face repohf_repo1
Pipeline tagpipeline_tag1
Model cardmodel_card_url1
Downloadsmetric.downloads1
Likesmetric.likes1
Datasetsdatasets1
Gatedgated1
Hf inference providershf_inference_providers1
Is quantizedis_quantized1
Last modifiedlast_modified1
Library namelibrary_name1
License namelicense_name1
License urllicense_url1
Downloads all timemetric.downloads_all_time1
Model typemodel_type1
Weights availableweights_available1
Weights dtypeweights_dtype1
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
28
Source tiers
T228
Freshest observation
4 h ago
Conflicts
None
Source documents 3
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.
Data quality (56/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →