Expired85% confidenceFactTime unknown
Deploying the e4b version of Gemma 4 via Ollama requires a total model download of approximately 9.6GB.
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/3/2026
First Seen
Valid until: 9/1/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedOllama支持GGUF格式的量化模型，可以在消费级硬件（如16GB内存的笔记本电脑）上流畅运行7B-13B参数规模的模型64% similarUnverifiedThe Ollama Windows installer package is approximately 1.9 GB62% similarUnverifiedOllama uses quantization schemes such as Q4_K_M by default, reducing the VRAM requirement for a 31B-parameter model from approximately 62GB (FP16) to approximately 20GB.62% similarUnverifiedWith a proxy configured, Ollama model download speeds can reach 20-30 MB/s.61% similarUnverifiedIn an experimental configuration, Ollama identifies the 840M as having approximately 16 GB of VRAM (16193 MiB), with about 14.6 GiB available for the Vulkan device at load time.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/38374API
curl https://kongchang.com/api/v1/knowledge/claims/38374MCP
get_claim(id=38374)