# tiny-audio-granite-qwen-frozen-4 by Alex Kroman: Open Model Source: https://savrn.com/models/tiny-audio-granite-qwen-frozen-4 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve tiny-audio-granite-qwen-frozen-4 (13M 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 | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 12, 2026. [tiny-audio-granite-qwen-frozen-4 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/tiny-audio-granite-qwen-frozen-4/gpus) ## Model Card This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Excerpt from the card by Alex Kroman. ## Configuration Architecture ASRModel Vocabulary size 248,192 Model type asr_model ## Identity and Version Repository mazesmazes/tiny-audio-granite-qwen-frozen-4 Publisher Alex Kroman Task Feature extraction Modality Text Library transformers Parameters 13M parameters Languages Not stated by the source Revision 0289e7feac2d1ff4052e7390f212150d13c65937 First published 2026-10-05 Last updated 2026-10-07 ## Files and Weights 19 files, 339.7 MB in total. The weights are 3 files totalling 319.5 MB in bin, safetensors. Weights3 files · 319.5 MB Configuration11 files · 216.4 KB Tokenizer2 files · 20.0 MB Documentation1 file · 5.2 KB Other1 file · 7.8 KB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | adapter_model.safetensors | Weights | 269.2 MB | a1d0d0f7f86e | | model.safetensors | Weights | 50.4 MB | 2aae926199ca | | training_args.bin | Weights | 5.3 KB | 96b511d20174 | | adapter_config.json | Configuration | 1.3 KB | — | | alignment.py | Configuration | 9.4 KB | — | | asr_config.py | Configuration | 21.0 KB | — | | asr_modeling.py | Configuration | 115.6 KB | — | | asr_pipeline.py | Configuration | 17.5 KB | — | | asr_processing.py | Configuration | 9.0 KB | — | | config.json | Configuration | 8.9 KB | — | | diarization.py | Configuration | 25.4 KB | — | | generation_config.json | Configuration | 231 B | — | | preprocessor_config.json | Configuration | 457 B | — | | projectors.py | Configuration | 7.6 KB | — | | README.md | Documentation | 5.2 KB | — | | chat_template.jinja | Other | 7.8 KB | — | | .gitattributes | Repository | 1.6 KB | — | | tokenizer.json | Tokenizer | 20.0 MB | a454aca253aa | | tokenizer_config.json | Tokenizer | 1.2 KB | — | ## License and Download License Not stated by the source Access Open weights, no gate Download size 319.5 MB [Download from Alex Kroman](https://huggingface.co/mazesmazes/tiny-audio-granite-qwen-frozen-4) Released by Alex Kroman through its official repository on Hugging Face. ## Built From - Described by [arXiv:1910.09700](https://savrn.com/papers/quantifying-the-carbon-emissions-of-machine-learning) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 319.5 MB | | 16-bit | 0.0 GB | | 8-bit | 0.0 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About tiny-audio-granite-qwen-frozen-4 ### How much GPU memory does tiny-audio-granite-qwen-frozen-4 need? About 0 GB at 16-bit and 0 GB at 4-bit: the weights (13M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run tiny-audio-granite-qwen-frozen-4 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. ## Similar Models Model · Feature extraction ### [tiny-audio-granite-qwen-frozen-2](https://savrn.com/models/tiny-audio-granite-qwen-frozen-2) [Alex Kroman](https://savrn.com/model-publishers/mazesmazes) This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Open weights 13M parameters transformers [View model](https://savrn.com/models/tiny-audio-granite-qwen-frozen-2) Model · Feature extraction ### [Qwen3-Voice-Embedding-12Hz-1.7B](https://savrn.com/models/qwen3-voice-embedding-12hz-1-7b) [Markus](https://savrn.com/model-publishers/marksverdhei) Standalone ECAPA-TDNN voice encoder extracted from Qwen/Qwen3-TTS-12Hz-1.7B-Base. Produces 2048-dimensional x-vector speaker embeddings from audio. The encoder follows the ECAPA-TDNN architecture (Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification) and uses Res2Net blocks, squeeze-excitation attention, and attentive statistical pooling. Speaker embeddings can be stored and shared as SafeTensors files. These embeddings are designed to drive voice cloning in the Qwen3-TTS family. There are two main inference paths: the qwentts Python package and the vLLM-Omni serving API. The qwentts package wraps the TTS model and exposes generatevoiceclone. To… Open weights apache-2.0 12M parameters transformers [View model](https://savrn.com/models/qwen3-voice-embedding-12hz-1-7b) Model · Feature extraction ### [tiny-audio-granite-qwen-frozen-3](https://savrn.com/models/tiny-audio-granite-qwen-frozen-3) [Alex Kroman](https://savrn.com/model-publishers/mazesmazes) This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Open weights 15M parameters transformers [View model](https://savrn.com/models/tiny-audio-granite-qwen-frozen-3) Model · Feature extraction ### [Sovereign-Swarm-Coherence-v1](https://savrn.com/models/sovereign-swarm-coherence-v1) [Alfredo Medina](https://savrn.com/model-publishers/itsnotailabs) The Sovereign-Swarm-Coherence-v1 is a production-verified PyTorch Multi-Head Self-Attention Transformer model designed for Robotics & Micro-Drone Swarm Control. Unlike generic models with arbitrary weight reporting, this repository explicitly itemizes learned trainable parameters versus non-trainable positional encoding constants: - Trainable Learned Parameters (requiresgrad=True): 800,019 - Positional Encoding Constant Buffer Elements (posencoder.pe): 640,000 $$R = \left| \frac{1}{N} \sum{j=1}^{N} e^{i \thetaj} \right|$$ - Computes exact Kuramoto phase order parameter R and 2D Euclidean pairwise collision risk geometry for micro-drone swarms. Apache 2.0 License © ItsNotAI LABS Open weights apache-2.0 1M parameters [View model](https://savrn.com/models/sovereign-swarm-coherence-v1) Model · Feature extraction ### [Sovereign-Swarm-Coherence-v1-alpha](https://savrn.com/models/sovereign-swarm-coherence-v1-alpha) [Alfredo Medina](https://savrn.com/model-publishers/itsnotailabs) The Sovereign-Swarm-Coherence-v1-alpha repository contains the lightweight ONNX & WebAssembly (WASM) client-side package for running inference directly inside web browsers and mobile apps with 0ms server latency and zero cloud API infrastructure costs. - 100% Offline Capable: Zero network dependencies after initial WASM module download. Apache 2.0 License © ItsNotAI LABS Open weights apache-2.0 1M parameters [View model](https://savrn.com/models/sovereign-swarm-coherence-v1-alpha) Model · Feature extraction ### [bge-small-zh-v1.5](https://savrn.com/models/bge-small-zh-v1-5) [Beijing Academy of Artificial Intelligence](https://savrn.com/model-publishers/baai) More details please refer to our Github: FlagEmbedding. FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. And it also can be used in vector databases for LLMs. Updates - 10/12/2023: Release LLM-Embedder, a unified embedding model to support diverse retrieval augmentation needs for LLMs. Paper:fire: - 09/15/2023: The technical report of BGE has been released - 09/15/2023: The masive training data of BGE has been released - 09/12/2023: New models: - 09/07/2023: Update fine-tune code: Add script to mine hard negatives and support adding instruction during fine-tuning. - 08/09/2023: BGE… Open weights mit 24M parameters 512 tokens transformers [View model](https://savrn.com/models/bge-small-zh-v1-5) ## Alex Kroman [All models and datasets](https://savrn.com/model-publishers/mazesmazes) ## Versions - [0289e7feac2d](https://savrn.com/models/tiny-audio-granite-qwen-frozen-4/versions/0289e7feac2d) · current 2026-10-07 ## Explore More - [All feature extraction models](https://savrn.com/models/tasks/feature-extraction) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-07. - [Hugging Face record](https://huggingface.co/mazesmazes/tiny-audio-granite-qwen-frozen-4) - [How the hub is built](https://savrn.com/model-hub/methodology)