Phonon-2 needs about 1.3 GB of memory at Q8_0 (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.4 GB (Q4_K) to 1.3 GB (F16).
Phonon-2: 0.627B parameter English speech recognizer in GGUF format
Phonon-2 is a 0.627B parameter English speech recognizer in GGUF format. It is under 900 MB and achieves high accuracy on English ASR benchmarks. The model is open‑source and licensed CC‑BY‑4.0.
Good at
- English speech recognition
- Low‑memory deployment
- Fast inference on CPUs
Limits
- No vision support
- Requires CC‑BY‑4.0 license
- Context length not specified
Best for
- Dictation apps
- Transcribing meetings
- Batch audio transcription
Who it’s for. Developers building speech‑to‑text services and researchers needing an open‑source English ASR. The model is suitable for applications that require fast, accurate transcription on modest hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q8_0 | 0.7 GB | 1.3 GB | Fits | Get file → | |
| F16 | 1.3 GB | 1.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K (0.4 GB file, ~1 GB memory at 8k context). For 4 GB VRAM, Q4_K is also suitable. With 16 GB VRAM, Q8_0 (0.67 GB file, ~1.3 GB memory) or F16 (1.26 GB file, ~1.9 GB memory) can be used. Memory estimates are approximate.
What GPU do you need for Phonon-2?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is F16 (1.3 GB file, about 1.9 GB in use).
Which Phonon-2 quant should you choose?
Q8_0 (0.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is Q4_K at 0.4 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Phonon-2
How much VRAM does Phonon-2 need?
About 1.3 GB at Q8_0 with an 8K context window. That is the 0.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Phonon-2 on an 8 GB GPU?
Yes, with F16: the 1.3 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Phonon-2 GGUF?
It depends on the quant: Q4_K is 0.4 GB, Q8_0 is 0.7 GB, F16 is 1.3 GB.
Where can I download Phonon-2 GGUF?
The files are on Hugging Face in the cstr/phonon2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Phonon-2 use?
Hugging Face lists the license as cc-by-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Phonon-2 on 8 GB VRAM?
Yes, the Q4_K quantization requires about 1 GB of VRAM at 8k context.
Does Phonon-2 support multiple languages?
No, the model is trained only for English.