Phonon-2 released
Fermion Research · Model release
Source confirmed
Data as of September 30, 2026 · How the score is built
CurrentOpen WeightNon-Reasoning
Released September 2026N/A contextFermion Research model documentation
Phonon-2
Decision readingPhonon-2 is tracked, but not publicly ranked yet. Published speech or voice results from Phonon-2 launch evaluation appear below. They do not produce a weighted text-model score.
Released September 2026 — see all recent releases
Phonon-2 will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Share or export
Voice benchmark evidence
Phonon-2 launch evaluation is an owner-defined voice evaluation. Its result stays separate from BenchLM's weighted text-model ranking.
Seven-set mean WER
5.21%
LibriSpeech clean WER
1.72%
LibriSpeech other WER
3.92%
AMI WER
9.37%
Earnings-22 WER
6.96%
GigaSpeech WER
8.35%
SPGISpeech WER
3.70%
VoxPopuli WER
2.46%
Download
164 MB
Phonon-2 (MLX)
174.0x realtime on M5 MacBook Air
Fermion-run; Fermion launch table retrieved September 30, 2026. Lower WER is better; throughput excludes model load.
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Radar
Full release historyPhonon-2 release history
Radar confirmed these at the source. Use Phonon-2 in your work? Explore Radar to follow supported changes and choose your alerts.
Radar
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not publishedFermion Research model documentation
- Context window
- N/A
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Open English speech recognition weights under CC-BY-4.0, derived from NVIDIA Parakeet TDT 0.6B v3. The 164 MB download stores encoder weights at about 2.1 bits; engines expand or requantize them at load, so download size is not runtime memory use. Runs through MLX on Apple silicon, CPU engines on Linux and Windows, and CUDA on NVIDIA GPUs. The launch page leaves the release day pending; the release ledger records September 2026.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordFermion Research model documentation
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Phonon-2, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
Phonon-2 is a open weight model with a N/A context window. No explicit reasoning mode is documented in this profile.
Open English speech recognition weights under CC-BY-4.0, derived from NVIDIA Parakeet TDT 0.6B v3. The 164 MB download stores encoder weights at about 2.1 bits; engines expand or requantize them at load, so download size is not runtime memory use. Runs through MLX on Apple silicon, CPU engines on Linux and Windows, and CUDA on NVIDIA GPUs. The launch page leaves the release day pending; the release ledger records September 2026.
Phonon-2 is tracked with speech recognition results from Fermion's Phonon-2 launch evaluation. These results are display-only and stay separate from weighted text-model rankings.
Its explicit predecessor is Phonon-1. Speech or voice evidence appears above; text-model benchmark coverage remains empty.
Last updated September 30, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersQuestions
How does Phonon-2 perform overall in AI benchmarks?
Phonon-2 has published speech or voice results in Phonon-2 launch evaluation. Those results remain separate from the weighted text-model ranking, so this profile does not assign a BenchLM score or overall rank. Use the linked evaluation's metric and run conditions to compare speech systems.
Is Phonon-2 open source?
Phonon-2 is an open-weight model from Fermion Research. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Does Phonon-2 have full benchmark coverage on BenchLM?
No. Phonon-2's speech or voice results appear in Phonon-2 launch evaluation, but it has no published text-model benchmark rows. The voice evaluation does not fill the text-model coverage slots or produce an overall rank. Missing text coverage is not treated as a zero score.
What is the context window size of Phonon-2?
Phonon-2 has a reported context window of N/A in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.