Verified85% confidenceBenchmarkExact time
After quantization, EmbeddingGemma 2 requires only approximately 191 MB of active memory for text-only weights on the Google Pixel 11 Pro, while the full multimodal model requires approximately 567 MB.
5
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
10/6/2026
First Seen
Valid until: 1/4/2027
Sources
Related Entities
Related Claims
UnverifiedEmbedding Gemma 2 has 740 million parameters, consisting of a 270M text encoder, a 170M vision encoder, and a 300M audio encoder, with runtime dynamic memory of approximately 191MB to 567MB; the 270M version requires a minimum of 0.5GB memory to run, and the full multimodal version can run locally with 1GB of memory.73% similarVerifiedMemory requirements are at least 37.6 GB for Q2_0, at least 39.2 GB for IQ2_XS, and at least 47 GB for IQ3_XXS, with the vision encoder occupying an additional 0.91 GB.69% similarUnverifiedThe Qwen 9B text test process has a peak memory usage of approximately 6.5 GB, while the peak memory usage spikes to approximately 10.8 GB when the vision module runs image tests.67% similarUnverified该1-bit量化的27B模型能够在仅8GB内存的设备上运行67% similarUnverified通义千问3-27B满血版需要55.6GB显存，而量化版仅需17GB66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/982383API
curl https://kongchang.com/api/v1/knowledge/claims/982383MCP
get_claim(id=982383)