Unverified50% confidenceFactExact time
Oído uses NVIDIA's Conformer-CTC Small model, which has approximately 13 million (13M) parameters and has been processed with int8 quantization.
1
Sources
50%
Confidence
Long-term
Relevance
9/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedConstrained by consumer-grade hardware (especially VRAM), Ollama can typically only run quantized models with 7B–13B parameters.65% similarUnverifiedTTM 模型参数量仅约 0.8M（百万级），文件大小约三兆字节，无需 GPU，在普通 CPU 上就能运行65% similarUnverifiedCurrent mainstream consumer-grade GPUs such as the NVIDIA RTX 4090 can already run quantized models with 7 billion to 13 billion parameters smoothly.63% similarUnverifiedNewer large-parameter models such as Flux have higher VRAM requirements, and the 3060 12GB can run quantized versions but with compromised speed.63% similarUnverified原本需要 A100 80GB 才能完成的 70B 参数模型微调任务，在 Unsloth 优化下可以在消费级 RTX 4090（24GB）上运行63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/962419API
curl https://kongchang.com/api/v1/knowledge/claims/962419MCP
get_claim(id=962419)