parakeet-tdt-0.6b-v3
Q4 GGUF download: handy-computer/parakeet-tdt-0.6b-v3-gguf - 0.49 GB on disk, read 2026-11-19. VRAM figures above are estimates; this is the actual file size.
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve nvidia/parakeet-tdt-0.6b-v3New to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
parakeet-tdt-0.6b-v3 is an open-weight speech recognition model published by nvidia on Hugging Face in August 2025, with 630M parameters under the cc-by-4.0 license.
Among the 25 speech recognition models in this directory it ranks 11th by monthly Hugging Face downloads, and 12 of the others are larger.
HardwareLink to this section
Unquantized FP16 weights take about 1 GB; 8-bit brings that to ~1 GB and 4-bit (Q4_K_M) to ~1 GB, before activations and any context or image buffers. At this size it runs on almost any recent GPU, on Apple Silicon, and usable on a modern CPU. Check exact numbers for your card with the VRAM calculator.
Similar speech recognition modelsLink to this section
- Whisper Large V3 Turbo - 800M, 4,713,890 downloads/month
- distil-large-v3 - 760M, 745,014 downloads/month
- Qwen3-ASR-0.6B-hf - 780M, 532,640 downloads/month
- nemotron-3.5-asr-streaming-0.6b - 640M, 448,774 downloads/month
- parakeet-ultra - 630M, 12,420 downloads/month
PopularityLink to this section
parakeet-tdt-0.6b-v3 was downloaded 531,382 times on Hugging Face in the last month (4,069,598 all-time) and has 1,292 likes.
Run it locallyLink to this section
Weights and usage instructions are on the nvidia/parakeet-tdt-0.6b-v3 model card; it loads with Hugging Face Transformers.
Local runtimes that fit this model:
- ollama - one-command local inference once a GGUF build is available
- llama-cpp - the GGUF engine underneath most local runners
- lm-studio - a desktop app for downloading and chatting with GGUF models
- vllm - high-throughput serving on NVIDIA GPUs
- transformers - the reference Python library most model cards target
PaperLink to this section
From the community
What users are saying
“Excellent transcription model. Please support Japanese language so that I can switch from Whisper to this model.”
“One documented option is NVIDIA Speech NIM if you mean serving completed recordings over HTTP/gRPC. The [26.10 support matrix](https://docs.nvidia.com/nim/speech/26.10.0/reference/support-matrix/asr.htmlparakeet-0-6b-tdt) maps type=multi to Parakeet-TDT-0.6B-v3.”
“Alternatively, you can skip installing nemo and torch and use the [onnx-asr](https://github.com/istupakov/onnx-asr) package to run the model.”
Frequently asked
Quick answers to common questions
How much VRAM does parakeet-tdt-0.6b-v3 need?
parakeet-tdt-0.6b-v3 with 630M parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is parakeet-tdt-0.6b-v3 better than other nvidia models?
parakeet-tdt-0.6b-v3 has 630M parameters - a strong choice for speech-recognition.
What license is parakeet-tdt-0.6b-v3 under?
parakeet-tdt-0.6b-v3 is released under the cc-by-4.0 license, making it suitable for most commercial and personal projects.
What hardware runs parakeet-tdt-0.6b-v3 well?
With 630M parameters, parakeet-tdt-0.6b-v3 is small enough for most consumer GPUs, Apple Silicon Macs, and many CPUs. Check our hardware directory for specific recommendations.
What is the best quantization for parakeet-tdt-0.6b-v3?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
What models compete with parakeet-tdt-0.6b-v3?
parakeet-tdt-0.6b-v3 competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec