Primary sources last checked on 13 Nov 2026. Verification freshness is tracked separately from factual change, and unknown values remain explicit rather than inferred.
NotableDistinct official first-party checkpoint with substantive specialist value; publisher rankings do not establish Leading.Curation method →
Open Model Weights records Phonon 31M English as a 31M acoustic model, excluding Mimi codec (publisher)-parameter text to speech open-weight model in the Phonon family, with Gradium listed as the developer. The checked source repository provides 4 recognized weight artifacts, format evidence for GGUF, Safetensors and a verified context window of 8,192 tokens. Values that are not evidenced in the checked sources remain explicitly undisclosed or unknown.
The repository declares apache-2.0. Commercial use allowed under apache-2.0 conditions. Open Model Weights reports the checked license evidence and classification; this is not legal advice.
No base model is declared in the checked standard lineage metadata, so Open Model Weights does not infer one. Training recipe status: not-disclosed-in-checked-repository; data disclosure status: not-disclosed-in-standard-metadata-or-obvious-model-card-section.
Phonon 31M English is a distinct official on-device streaming english speech release by Gradium. This profile separates immutable original weight artifacts, license restrictions, publisher descriptions and independently measured evidence. Open Model Weights independently inspected the exact repository revision, listed weight artifacts and declared license; it has not run the model or reproduced publisher benchmark results. The source verifier found a model-card and repository license declaration, not a separately checked standard license file.
Source evidence 1Publisher states 31M parameters excluding Mimi audio tokenizer and a 24kHz mono speech format.Source ↗
Source evidence 2The model emits 80ms acoustic latent frames requiring Mimi decode and a compatible native runtime.Source ↗
Source evidence 3This 31M English checkpoint is Apache-2.0 whereas the 40M multilingual family is CC BY-NC 4.0.Source ↗
Source evidence 4GGUF and Safetensors artifacts, where present, must be separately identified rather than declared identical.Source ↗
Official immutable revision92741c5b07d085ff840e26fea8ce43110b87852fSource ↗
Model license evidenceapache-2.0; declared-metadata-checkedSource ↗
Commercial-use statusallowed; see exact model-specific termsSource ↗
Repository cardREADME and source-described usage; no independent OMW inference runSource ↗
Performance provenancePublisher metrics, if mentioned, are not independent OMW measurementsSource ↗
WHY IT MATTERS
Publisher states 31M parameters excluding Mimi audio tokenizer and a 24kHz mono speech format. This refers to the specific source checkpoint gradium/phonon-31m-en rather than an inferred family rank, unverified local benchmark or third-party quantization.
This 31M English checkpoint is Apache-2.0 whereas the 40M multilingual family is CC BY-NC 4.0. The original model-card license tag is apache-2.0; the catalog's supported parser classification is apache-2.0, and commercial-use is allowed. Publisher permissions require exact-text interpretation.
GGUF and Safetensors artifacts, where present, must be separately identified rather than declared identical. Evaluation conditions such as prompts, hardware, specialized test suites and model formatting matter. Open Model Weights has not reproduced the publisher's reported result.
MODEL-SELECTION VIEW
Strong fit when…
Publisher states 31M parameters excluding Mimi audio tokenizer and a 24kHz mono speech format. This refers to the specific source checkpoint gradium/phonon-31m-en rather than an inferred family rank, unverified local benchmark or third-party quantization.
A reproducible evaluation of Phonon 31M English should pin 92741c5b07d085ff840e26fea8ce43110b87852f, compare against a suitable verified counterpart, report actual memory and quality measurements, and record failures rather than infer success from marketing claims.
Publisher states 31M parameters excluding Mimi audio tokenizer and a 24kHz mono speech format.
Important considerations
Metadata, original weight files, readme, architecture configuration and the repository's associated license evidence were checked in a live source audit. File manifests are not claims of a completed OMW inference run.
The legal grant for weights can differ from source-code, third-party codec, hosted API and downstream distribution terms. Restrictions remain visible even where the repository uses an attractive open-weights marketing label.
Compute memory includes KV caching, framework overhead, inference batching, activations and separately loaded encoders or processors. Theoretical weight-only values cannot be presented as measured peak VRAM.
Purpose, modality and official checkpoint
Publisher states 31M parameters excluding Mimi audio tokenizer and a 24kHz mono speech format. This refers to the specific source checkpoint gradium/phonon-31m-en rather than an inferred family rank, unverified local benchmark or third-party quantization.
The official model card describes the intended functionality and available repository content. Public access to its metadata does not itself demonstrate an unrestricted commercial license or performance across arbitrary workloads.
Original weights and exact provenance
The model emits 80ms acoustic latent frames requiring Mimi decode and a compatible native runtime. It is pinned at exact official SHA 92741c5b07d085ff840e26fea8ce43110b87852f. The verifier identified 4 original weight artifacts, with access public. Keep tokenizers and processors matched.
Metadata, original weight files, readme, architecture configuration and the repository's associated license evidence were checked in a live source audit. File manifests are not claims of a completed OMW inference run.
Model license and use restrictions
This 31M English checkpoint is Apache-2.0 whereas the 40M multilingual family is CC BY-NC 4.0. The original model-card license tag is apache-2.0; the catalog's supported parser classification is apache-2.0, and commercial-use is allowed. Publisher permissions require exact-text interpretation.
The legal grant for weights can differ from source-code, third-party codec, hosted API and downstream distribution terms. Restrictions remain visible even where the repository uses an attractive open-weights marketing label.
Publisher evaluations versus independent results
GGUF and Safetensors artifacts, where present, must be separately identified rather than declared identical. Evaluation conditions such as prompts, hardware, specialized test suites and model formatting matter. Open Model Weights has not reproduced the publisher's reported result.
Independent category comparison is only linked when a relevant external assessment exists and the tested variant is identified. Publisher-only figures are never converted into OMW benchmark measurements.
Runtime integration and operational limits
Phonon 31M English needs architecture-compatible model code, configuration, tokenization and processing and may require dedicated accelerators, audio decoding or specialized multimodal pipelines. Software integration is not independently validated by this catalog.
Compute memory includes KV caching, framework overhead, inference batching, activations and separately loaded encoders or processors. Theoretical weight-only values cannot be presented as measured peak VRAM.
Reproducible deployment and comparison
A reproducible evaluation of Phonon 31M English should pin 92741c5b07d085ff840e26fea8ce43110b87852f, compare against a suitable verified counterpart, report actual memory and quality measurements, and record failures rather than infer success from marketing claims.
Preserving original hashes, license evidence, expected context assumptions, runtime versions and explicit test cases is necessary to distinguish a reliable deployment from a plausible-looking unverified example.
IMPLEMENTATION & EVALUATION
How to evaluate Phonon 31M English before deployment
Reproducible operator checklist; these steps are not claims of an OMW model run.
STEP 01
Pin original source and weight manifest
A named model does not guarantee identical checkpoint revisions.
REPRODUCIBLE ACCEPTANCE TEST
Record 40-character SHA, original file names, configuration and tokenizer/processor versions.
WHAT CAN GO WRONG
Unpinned revisions can silently change weights or usage requirements.
STEP 02
Reproduce task-specific inputs
A specialist checkpoint can fail outside the publisher's demonstrated conditions.
REPRODUCIBLE ACCEPTANCE TEST
Document actual prompt templates, modality preprocessing, inference backend and compatible software versions.
WHAT CAN GO WRONG
Using unsupported serving backends can invalidate comparisons.
STEP 03
Audit license and operational controls
Model card labels and code licenses are not automatically permission for every deployed use.
REPRODUCIBLE ACCEPTANCE TEST
Check exact weight terms, notices, tool permissions, data privacy and runtime isolation.
WHAT CAN GO WRONG
Restricted weight rights or unsafe action tools can make a deployment unsuitable.
STEP 04
Publish independent results only if measured
Vendor benchmark figures are useful evidence, but are not OMW-run observations.
REPRODUCIBLE ACCEPTANCE TEST
Pre-register held-out tasks and compare baseline checkpoint, hardware, quality, memory and error rates.
WHAT CAN GO WRONG
Attributing first-party results to independent inference would mislead readers.
Publisher states 31M parameters excluding Mimi audio tokenizer and a 24kHz mono speech format.
Are original weights accessible?
Official gradium/phonon-31m-en has 4 checked artifact entries at 92741c5b07d085ff840e26fea8ce43110b87852f; access is public. Gated downloads may require authorization.
What rights apply?
This 31M English checkpoint is Apache-2.0 whereas the 40M multilingual family is CC BY-NC 4.0. apache-2.0 is source metadata, while the field verifier records apache-2.0.
Are model performance claims independently reproduced?
GGUF and Safetensors artifacts, where present, must be separately identified rather than declared identical. OMW has not performed an independent inference benchmark.
What runtime considerations matter?
The model emits 80ms acoustic latent frames requiring Mimi decode and a compatible native runtime. Compatible architecture code, preprocessing and full resource planning remain essential.
Why is the model curated?
Official weights and distinctive task relevance justify Notable without fabricating a benchmark rank.
03 · PRACTICAL TECHNICAL PROFILE
Deployment, licensing and reproducible evidence.
Inspect weight-memory estimates, model lineage and runtime evidence separately from promotional or untested performance claims.
DEPLOYMENT PROFILE
Weight memory, without pretending it is a deployment guarantee.
These bars visualize weight-only decimal-GB estimates. They exclude KV cache, activations, runtime overhead, optimizer state and sharding.
WEIGHT-ONLY MEMORY
BF16 / FP16~0.1 GB
FP8 / INT8~0.0 GB
INT4~0.0 GB
FIELD EVIDENCE MAP
WeightsVerified
LicenseVerified
Commercial useAllowed
ContextVerified
FormatsVerified
LineageNot declared
Training recipeNot disclosed in checked repository
Training dataNot disclosed in standard metadata or obvious model card section
RuntimeSource-derived · not runtime-tested
LICENSE & USE
apache-2.0
Commercial use allowed under apache-2.0 conditions
Declared licenseapache-2.0
ClassificationAllowed
VerificationDeclared metadata checked
This section summarizes the checked repository evidence. It is not legal advice.
LINEAGE & PROVENANCE
What the checked sources disclose — and what they do not.
Open Model Weights does not infer a hidden base model or training corpus when the checked sources do not declare one.
LINEAGE
BASE / PARENTNot declared in model-card metadataUnknown
not inferred
CURRENT RECORDPhonon 31M EnglishPhonon
TRAINING DISCLOSURE
Training recipeNot disclosed in checked repository
Training dataNot disclosed in standard metadata or obvious model card section
FamilyPhonon
RUNTIME SIGNALS
Compatibility claims stay attached to their evidence level.
Declared and model-card-mentioned runtimes are discovery signals. They are not treated as Open Model Weights runtime tests unless explicitly measured.
Declaredtransformers
MentionedTransformers
OMW runtime testNot performed
EVIDENCE TRAIL
Sources and observed history.
This is where the article remains auditable: source links on one side, the registry's observed change history on the other.
Phonon 31M English: technical evidence at a glance
Three evidence-linked visual summaries: parameter scale, illustrative precision memory and verifiable provenance. No performance ranking is implied.
01 / PARAMETER SCALE
Total versus active parameters
Total parameters0.03B
Active parameter count not established.
Publisher-described logical parameter count
Published total parameters are not a model-quality or performance score.
02 / MEMORY ESTIMATE
Weight-only precision footprint
BF16 / FP160.08 GB
FP8 / INT80.04 GB
INT40.02 GB
Hypothetical weight-only decimal GB, not measured peak VRAM or guaranteed support for each format. KV cache, activations, runtime and sharding are excluded.
Weight artifacts4 recognized artifacts · public access
03
License declarationapache-2.0Metadata declaration
04
Latest published source check
Repository SHA 92741c5b07d0…; a source check is not an inference benchmark or legal clearance. See the per-model evidence JSON for the exact source record.
A verification check does not pretend the model changed. Open Model Weights updates the verification date after a real primary-source check, while factual-update dates move only when retained source evidence changes.
Commercial useCommercial use allowed under apache-2.0 conditions
Repository license filesNone observed
Classification describes the checked license terms; it is not legal advice.
03 · HARDWARE
Weight-memory estimate
BF16 / FP16~0.1 GB
FP8 / INT8~0.0 GB
INT4~0.0 GB
Weight-only decimal-GB estimate from total parameter count; excludes KV cache, activations, runtime overhead, optimizer state and sharding.
04 · FORMATS
Formats & precision evidence
GGUFSafetensors
BF16: not observedFP16: not observedFP8: not observedINT8: not observedINT4: not observedGGUF: observed
“Not observed” means no matching repository artifact/name/dtype signal was found; it does not prove no third-party conversion exists.
05 · LINEAGE
Base model & family
FamilyPhonon
Variant31M English
Declared base modelNot declared in model-card metadata
RelationNot declared
06 · TRAINING ASSETS
Recipe & data disclosure
Training recipenot-disclosed-in-checked-repository
Data disclosurenot-disclosed-in-standard-metadata-or-obvious-model-card-section
EvaluationsNot classified by automated verifier
Intermediate checkpointsNot classified by automated verifier
07 · RUNTIME SUPPORT
Declared, mentioned and externally evidenced runtimes
Declared librarytransformers
Declared/taggedtransformers
Mentioned in model cardTransformers
Artifact signalsNone
External primary runtime evidenceNone
Tested by Open Model WeightsNo — source-derived support only
Open Model Weights separates model-repository evidence from external runtime-release evidence. An external support statement does not change the official model repository's weight formats and does not imply an Open Model Weights inference benchmark.
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Repository revision check
Official Hugging Face repository SHA unchanged; prior field evidence retained.
Field-by-field verification
Checked Hugging Face API metadata, exact repository file list, model card and config when accessible.
licenseverified
commercial useclassified
contextverified
weight filesverified
formatsverified
base modelnot-declared
training recipenot-disclosed-in-checked-repository
data disclosurenot-disclosed-in-standard-metadata-or-obvious-model-card-section
runtime supportsource-derived-not-runtime-tested
MODELS FOR AI AGENTS · ROLE EVIDENCE
Where this model fits in an agent system
Specialized model. A supporting component. This checkpoint does not, by category alone, serve as the planning and tool-execution controller.
The curated notable tier is not an agent-readiness rating. Model-specific tool-call success, long-horizon task accuracy and compatible runtime configurations are not independently established here.
Source-linked license: apache-2.0 (allowed commercial-use classification; see original terms).
Context: 8192 configured tokens.
BF16 weights: 0.08 estimated decimal GB, not runtime VRAM.