Expired75% confidenceFactTime unknown
The model file size of GPT-OSS 120B is approximately 60.8 GB, having undergone approximately 4-bit quantization.
1
Sources
75%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedThe minimum VRAM requirement for running GPT-OSS-20B is 16GB, and the model file size is approximately 41.3GB.81% similarUnverifiedGPT-OSS 20B运行时内存占用约10GB，显存占用约14.5GB80% similarUnverifiedThe KV cache for a 128K context window of a GPT-4-level model can occupy tens of gigabytes of VRAM79% similarUnverifiedGPT-3 has 175 billion parameters, and storing these weights alone requires hundreds of gigabytes of space71% similarUnverifiedA 300B INT4 quantized model requires approximately 150–180GB of storage space.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/23253API
curl https://kongchang.com/api/v1/knowledge/claims/23253MCP
get_claim(id=23253)