Unverified50% confidenceFactExact time
Hy-Memory-30B-A3B uses the Hunyuan sparse expert (MoE) architecture, with about 30 billion total parameters and only about 3 billion parameters activated per forward pass.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMoE模型采用稀疏激活，Qwen 3.5 122B总参数122B但每次推理仅激活约10B，需将全部参数加载进内存，对内存容量极度敏感71% similarUnverifiedTaking the LLaMA-3 70B model as an example, with 80 layers, head_dim=128, and BF16 precision, each token occupies approximately 80KB of KV cache.70% similarUnverifiedCombining MoE with quantization technology can make it possible for a laptop with 16 GB of memory to run MoE models with tens of billions of parameters.69% similarUnverifiedOn the 2.8-trillion-parameter KimiK3, the per-megawatt throughput of GB300-NVL72 is about 80 times that of H200, while pushing interactivity to about 215 tokens/second/user.68% similarUnverifiedHy-Memory-30B-A3B uses the HYV3ForCausalLM architecture, with 128 routed experts and 8 activated per token, 48 layers, hidden dimension 2048, max position embeddings 262,144, and support for Chinese and English.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1070510API
curl https://kongchang.com/api/v1/knowledge/claims/1070510MCP
get_claim(id=1070510)