Unverified50% confidenceFactExact time
Gemma is available in different scales including 2B (2 billion parameters) and 7B/9B (7–9 billion parameters), and the 2B model can run on ordinary consumer-grade GPUs or even some high-performance CPUs.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
Unverified2B-parameter-scale models can run on a single consumer-grade GPU (e.g., RTX 3090/4090 with 24 GB VRAM) or even in some CPU inference scenarios.77% similarUnverifiedCurrent mainstream consumer-grade GPUs such as the NVIDIA RTX 4090 can already run quantized models with 7 billion to 13 billion parameters smoothly.70% similarUnverifiedGemma 3 offers multiple sizes covering different hardware, including a minimum version of approximately 1GB, medium-sized versions, and large versions such as 12B and 27B.69% similarUnverifiedModels at the 9B parameter scale can already complete low-precision fine-tuning on consumer-grade GPUs such as the NVIDIA RTX 4090 (24 GB VRAM).68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1004029API
curl https://kongchang.com/api/v1/knowledge/claims/1004029MCP
get_claim(id=1004029)