Unverified50% confidenceFactExact time
SaluNet's training was completed on a single shared NVIDIA A40 (24 GB).
1
Sources
50%
Confidence
Long-term
Relevance
11/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBaidu open-sourced ERNIE 5.5 Flash Base, with 280B parameters, sparse MoE activating 14B, domain training on 33.5 trillion Tokens, and support for a 128K training context.60% similarUnverifiedLoRA's design compresses the number of trainable parameters by more than 99%, allowing a 7B-parameter model to be fine-tuned on a single consumer-grade GPU with 24GB of VRAM (such as the RTX 3090/4090).60% similarUnverifiedThe entire Laya model was trained on a single RTX 6000 Pro (96 GB VRAM).57% similarVerifiedModels with 32B parameters can typically be compressed to approximately 16–20 GB of VRAM usage after quantization, and can be run on a single NVIDIA RTX 4090 (24 GB VRAM).57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1151071API
curl https://kongchang.com/api/v1/knowledge/claims/1151071MCP
get_claim(id=1151071)