Unverified50% confidenceFactExact time
The candidate lineup ranges from the 0.70GB LFM 1.2B to the 24.57GB Nemotron 3 Nano 30B-A3B.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedIn Nemotron 3 Nano 30B-A3B, 30B refers to a total parameter count of approximately 30 billion, while A3B indicates that approximately 3 billion parameters are actually activated per forward pass; the model weights still need to be fully loaded, and the runtime memory footprint is similar to that of a dense large model.75% similarUnverifiedThe boot log shows that the expected configuration is 8 Gbit (0x07) and the actual configuration is 32 Gbit (0x05).65% 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83GB64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1003723API
curl https://kongchang.com/api/v1/knowledge/claims/1003723MCP
get_claim(id=1003723)