Unverified50% confidenceFactExact time
The model has 1.91M parameters, and after int8 quantization the weights occupy 1.97 MB, which is 49.8% of the Ryzen 5 3400G's 4 MB L3 cache.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe additional 64MB of SRAM stacked on the Ryzen 7 5800X3D doubles the total L3 cache from 32MB to 96MB.75% similarVerifiedA 7B-parameter model requires only approximately 4 GB of VRAM to run after 4-bit quantization.73% similarUnverifiedAWQ和GGUF均能将700亿参数模型存储体积从FP16的约140GB压缩至INT4的约35-40GB，可在单张RTX 4090上运行，精度损失通常控制在1-3%以内72% similarUnverifiedA100 80GB通过MIG最多可切分为7个1g.10gb实例（每个约10GB显存），也可切分为2g、3g、4g、7g规格实例71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1006036API
curl https://kongchang.com/api/v1/knowledge/claims/1006036MCP
get_claim(id=1006036)