Unverified50% confidenceEventExact time
A developer named hellohazine reduced the Unsloth quantized version of Kimi K3 from 711 GB to 478 GB.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedThe Tencent team compressed a 3.3 GB translation model down to 440 MB, a compression ratio of nearly 87%, with almost no visible degradation in BLEU score.69% similarUnverifiedK3s是Rancher推出的轻量Kubernetes发行版，将整个Kubernetes控制平面压缩到约70MB64% similarUnverifiedQ3_K_M compresses each weight to approximately 3 bits, reducing the weight size of a 27B model to approximately 12–13 GB.62% similarUnverifiedBonsai compresses a 27B model from 54GB at full precision down to 3.9GB62% similarUnverifiedOn MI355X, by removing unnecessary expert padding, the FP4 MoE model weights of DeepSeek-V4 were reduced from 159.07 GB to 112.36 GB.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/909845API
curl https://kongchang.com/api/v1/knowledge/claims/909845MCP
get_claim(id=909845)