// Open-model VRAM table · family
FunAudioLLM speech: local deployment & VRAM
5 open-weight models from Alibaba Tongyi Lab (8 official repos incl. quantised builds).
official orgs: FunAudioLLMlatest 2026-05-24memory = estimate
01Speech-to-text (3)
| Model | Params | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|
| Fun-ASR-Nano-2512-hf | 830M | 2.3 GB | 1.1 GB | 8GB GPU | Mac 16GB | Commercial OK | 2026-05-24 |
| Fun-ASR-MLT-Nano-2512 | — | — | — | — | — | Commercial OK | 2025-12-15 |
| SenseVoiceSmall | — | — | — | — | — | Custom licence – read it | 2024-07-03 |
02Text-to-speech / audio (2)
| Model | Params | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|
| Fun-CosyVoice3-0.5B-2512 | 500M | 1.6 GB | 0.8 GB | 8GB GPU | Mac 16GB | Commercial OK | 2025-12-11 |
| CosyVoice2-0.5B | 500M | 1.6 GB | 0.8 GB | 8GB GPU | Mac 16GB | Commercial OK | 2025-07-29 |
03Other families
Qwen · IBM Granite · NVIDIA Nemotron · Gemma · Mistral / Magistral / Devstral · GLM / CogVideoX (Z.ai) · DeepSeek · Ai2 OLMo / Molmo · Ant Ling / Ring / Ming · Liquid LFM · MiniCPM / VoxCPM · Tencent Hunyuan / Hy · Phi · Llama · Meituan LongCat · Jina embeddings & rerankers · Wan · Kimi · Cohere Command / Aya · Xiaomi MiMo · FLUX · Microsoft VibeVoice / Fara / Harrier · InternLM / Intern-S · StepFun Step · MiniMax · Baidu ERNIE · NVIDIA Parakeet / Canary speech · Stable Diffusion / Stable Audio · Yi (01.AI) · ByteDance Seed · SmolLM / SmolVLM · BGE embeddings & rerankers · LTX Video · gpt-oss · poolside Laguna · Whisper · Baichuan · Thinking Machines Inkling · xAI Grok · rednote dots
Totals include 10% + 0.5GB overhead and one 8K-token KV cache for text models. Estimates only. Method →