Unverified50% confidenceFactExact time
Saluki 27B can run locally on CPU or GPU via llama.cpp and also supports Docker containerized deployment.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/10/2026
First Seen
Valid until: 1/8/2027
Sources
Related Entities
Related Claims
Unverifiedllama.cpp supports hybrid CPU+GPU inference, controls the number of layers offloaded to the GPU via the --n-gpu-layers parameter, and includes a built-in HTTP server compatible with the OpenAI API format.64% similarUnverifiedllama.cpp支持在CPU上高效运行量化模型，Ollama提供一体化的本地模型管理和API服务63% similarUnverifiedCommonly used local deployment toolchains include llama.cpp (CPU/GPU hybrid inference) and Ollama (a local server that packages quantized models).63% similarUnverified运行本地LLM推理至少需要配备NVIDIA A10G或更高级别GPU，纯API调用模式下CPU实例即可满足需求60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/994996API
curl https://kongchang.com/api/v1/knowledge/claims/994996MCP
get_claim(id=994996)