This model was converted to MLX format from nvidia/parakeet-tdt-0.6b-v3 using the conversion script. Please refer to original model card for more details on the model.
Open-weight model · Speech recognition
fluid-speech-mini-mlx-4bit
by David Larrea davidalarrea/fluid-speech-mini-mlx-4bit
fluid-speech-mini-mlx-4bit is an open-weight model for speech recognition from David Larrea, released under Creative Commons Attribution 4.0. It has 627M parameters. At 16-bit it needs about 1.5 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Parameters627M
Context—
Weights—
Licensecc-by-4.0
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve fluid-speech-mini-mlx-4bit (627M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 1.3 GB | 1.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.6 GB | 0.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.3 GB | 0.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 24, 2026.
fluid-speech-mini-mlx-4bit on every accelerator the SAVRN Index prices, at every precision
Model Card
Identity and Version
- Repository
- davidalarrea/fluid-speech-mini-mlx-4bit
- Publisher
- David Larrea
- Task
- Speech recognition
- Modality
- Audio
- Library
- mlx
- Parameters
- 627M parameters
- Languages
- en
- Revision
- f09ca26fb810d2b95dbea74233415694cc2b6257
- First published
- 2026-10-22
- Last updated
- 2026-10-22
License and Download
- License
- cc-by-4.0
- Access
- Open weights, no gate
Download from David Larrea
Released by David Larrea through its official repository on Hugging Face. Read the license.
Built From
- Derived from apiplant/fluid-speech-mini-safetensors
Memory Requirements
| Precision | Weights in memory |
|---|---|
| 16-bit | 1.3 GB |
| 8-bit | 0.6 GB |
| 4-bit | 0.3 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About fluid-speech-mini-mlx-4bit
How much GPU memory does fluid-speech-mini-mlx-4bit need?
About 1.5 GB at 16-bit and 0.4 GB at 4-bit: the weights (627M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run fluid-speech-mini-mlx-4bit on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use fluid-speech-mini-mlx-4bit commercially?
Yes. fluid-speech-mini-mlx-4bit is released under Creative Commons Attribution 4.0. CC BY 4.0 permits sharing and adapting the work, including commercially, provided the creator is credited and changes are indicated.
Similar Models