Unverified50% confidenceFactExact time
Agens Volundr 32B is a dense architecture with approximately 32B parameters and 72 layers in total, of which only 18 layers retain KV cache.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen the context of LLaMA-2 7B is extended to 32K tokens, KV Cache GPU memory usage expands to approximately 16 GB, approaching the total memory of a single consumer-grade GPU.70% similarVerified以LLaMA-3 70B（80层、64头、每头128维）为例，单个token的KV Cache约占2.6MB（FP16精度），32K上下文的KV Cache总量约达83GB70% similarUnverifiedAgens Volundr 32B has a context window of 262K.69% similarVerifiedA single sequence of 32K context length for LLaMA-2 70B can require approximately 80 GB of KV cache in FP16.68% similarVerified32B参数规模的模型在量化后通常可以压缩到约16-20GB显存占用，一张NVIDIA RTX 4090（24GB显存）就能运行68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/977109API
curl https://kongchang.com/api/v1/knowledge/claims/977109MCP
get_claim(id=977109)