phonon refiner 1.7b needs about 0.8 GB of memory at its main file (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.2 GB to 1.0 GB (Q4_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 0.2 GB.
Phonon Refiner 1.7B – a lightweight text correction model for local voice‑typing
Phonon Refiner 1.7B is a 0.194B parameter text model fine‑tuned from LiquidAI/LFM3‑1.7B to rewrite raw transcripts into accurate speaker text. It runs locally on Apple Silicon Macs and other devices via the Phonon engine.
Good at
- reasoning
- tools
- voice‑transcript correction
Limits
- trained context 32768 tokens
- no vision support
- license is other
Best for
- correcting dictation transcripts
- tool‑calling in local agents
- structured text output
Who it’s for. Developers building local voice‑typing applications or agents that need accurate text from raw speech. The model is suitable for edge devices with limited memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q4_K_S | 1.0 GB | 1.5 GB | Fits | Get file → |
For 8 GB VRAM, the Q4_K_S quant (0.99 GB, 1.5 GB memory at 8 k context) is recommended. If memory is very tight, the unknown quant (0.21 GB, 0.8 GB memory) can be used, but it may lack full precision.
What GPU do you need for phonon refiner 1.7b?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 Q4_K_S (1.0 GB file, about 1.5 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about phonon refiner 1.7b
How much VRAM does phonon refiner 1.7b need?
About 0.8 GB at its main file with an 8K context window. That is the 0.2 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 refiner 1.7b on an 8 GB GPU?
Yes, with Q4_K_S: the 1.0 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of phonon refiner 1.7b GGUF?
It depends on the quant: file is 0.2 GB, Q4_K_S is 1.0 GB.
What context length does phonon refiner 1.7b support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.2 GB at 32K.
Where can I download phonon refiner 1.7b GGUF?
The files are on Hugging Face in the Infatoshi/phonon-refiner-1.7b 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 refiner 1.7b use?
Hugging Face lists the license as other. 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 Refiner 1.7B on 8 GB VRAM?
Yes, the Q4_K_S quant uses about 1.5 GB of VRAM at 8 k context, fitting within 8 GB.
Does this model support image input?
No, Phonon Refiner 1.7B is a text‑only model with no vision capabilities.
What is the context length of this model?
The model is trained with a context of 32768 tokens.