Text-to-speech Sourced statement
NeuTTS Air on NVIDIA GPU, 24 GB+ VRAM
Benchmark pending. We haven't measured this pair yet. Below is what the sources say about this hardware, quoted with links.
Enthusiast/prosumer. Runs nearly every open speech model, including 8B-class TTS.
EvidenceSourced statement
Commercial useYes
Licenseapache-2.0
Stated memoryNot stated
Device memory24 GB VRAM
Results
Benchmark pending. No measured numbers from us yet for NeuTTS Air on 24 GB+ GPU. Get notified or send us your numbers (with the method).
What the sources say about 24 GB+ GPU
- Model authors RTX 4090 (vLLM throughput benchmark): 16,194 tokens/s. sourceCaveat: Batch throughput, not single-stream latency
Method
We haven't run this pair. Everything on this page is quoted from the linked sources, with the source type labelled (model authors vs third parties). Vendor numbers are often measured under favourable conditions.
Ways to run NeuTTS Air
Run it
pip install "neutts[llama]" # GGUF backbones via llama-cpp-python; see README for Metal/BLAS build flagsCopied from the linked README. We haven't run it on this device.
Caveats
- Batch throughput, not single-stream latency