Unverified50% confidenceFactExact time
gpt-oss-120b has about 117B total parameters, but each token activates only about 5.1B parameters.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedThe parameter count of 124M is close to the scale of GPT-2 Small.73% similarVerifiedA GPT-4-class model with 175 billion parameters requires approximately 175 GB of VRAM even when stored at fp8 precision.68% similarUnverifiedOn NVIDIA L4, the bf16 model (6.32 GiB) has a theoretical memory-bandwidth ceiling of about 47 tokens/s, while the int4 model (2.85 GiB) has a theoretical ceiling of about 105 tokens/s, with measured peak reaching 131.9 tokens/s.66% similarUnverifiedOf this 125B model's backbone, approximately 121B is the Mixture-of-Experts (MoE) portion, with an additional approximately 51B PLE lookup table and approximately 4B MTP module, bringing the complete checkpoint close to 180B.66% similarUnverifiedMainstream GPU inference solutions (such as deployments based on NVIDIA H100) typically achieve only a few dozen to one or two hundred tokens per second on 27B-scale models.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1014107API
curl https://kongchang.com/api/v1/knowledge/claims/1014107MCP
get_claim(id=1014107)