Unverified50% confidenceFactExact time
Q4_K_M是llama.cpp生态中GGUF格式的主流量化方案，K代表K-quants（2023年引入），M代表Medium档位
1
Sources
50%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
UnverifiedThe k-quant quantization scheme was introduced in mid-2023 by ikawrakow, a core developer of the llama.cpp project66% similarUnverifiedThe Qwen 2.5 series was launched in 2024, covering a full range of open-source weights from 0.5B to 72B.62% similarUnverifiedQwen3于2025年4月发布，Dense模型引入QK RMS Norm，MoE模型取消共享专家并改用更细粒度专家切分配全局批量负载均衡损失，训练数据翻倍到36万亿Token59% similarVerifiedQLoRA was proposed by a research team at the University of Washington in 2023, quantizing base model weights to 4-bit (NF4 format)59% similarVerifiedQwen3 is a new generation open-source large model series released by Alibaba Cloud in 2025, supporting a hybrid reasoning mode.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/533679API
curl https://kongchang.com/api/v1/knowledge/claims/533679MCP
get_claim(id=533679)