Unverified50% confidenceFactExact time
Gemma 3's smaller model sizes (such as the 4B and 12B parameter versions) can run on consumer-grade GPUs.
1
Sources
50%
Confidence
Long-term
Relevance
9/1/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe Gemma series mainly includes versions with 2B and 7B parameter scales; the Gemma 3 series released in 2025 further expands to 27B and supports multimodal input.72% similarUnverified微软Phi-3最小版本仅3.8B参数，Google Gemma有2B和7B两个规格71% similarVerifiedThe Gemma 4 series includes four models: 1B, 2B, 4B, 26B (MOE), and 31B (Dense).70% similarUnverifiedGemma 4's 31B Dense model ranks third on the open-source model leaderboard.69% similarUnverifiedIf Gemma 3 12B frequently makes errors on structured output, it is recommended to switch to the Qwen 2.5 series or Llama 3.1 8B/70B, as they have better native support for Function Calling.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/839121API
curl https://kongchang.com/api/v1/knowledge/claims/839121MCP
get_claim(id=839121)