Spark Tts Nexvox V14 16bit is an open-source language model by crestai. Features: 506.6m LLM, VRAM: 2GB, Context: 32K, License: apache-2.0, Quantized.
16bit Base model:crestai/spark-tts-n... Base model:finetune:crestai/sp... Conversational En Endpoints compatible Quantized Qwen2 Region:us Safetensors Unsloth
Model Card on HF 🤗: https://huggingface.co/crestai/spark-tts-nexvox_v14_16bit
Spark Tts Nexvox V14 16bit Parameters and Internals
| LLM Name | Spark Tts Nexvox V14 16bit |
| Repository 🤗 | https://huggingface.co/crestai/spark-tts-nexvox_v14_16bit |
| Model Name | Spark-TTS-0.5B/LLM |
| Base Model(s) | |
| Model Size | 506.6m |
| Required VRAM | 2 GB |
| Updated | 2026-03-31 |
| Maintainer | crestai |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 16bit |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 166000 |
| Torch Data Type | float32 |
| Errors | replace |
Quantized Models of the Spark Tts Nexvox V14 16bit
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| Spark Tts Nexvox V14 16bit | 0 | 298 | 2 GB |
Rank the Spark Tts Nexvox V14 16bit Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52334 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a