Unverified70% confidenceReleaseExact time
The model catalog refresh added two providers, Boundless and Standard Compute; SambaNova is now fetched from the catalog, with MiniMax M3 as the default model.
2
Sources
70%
Confidence
Short-term (~14 days)
Relevance
10/16/2026
First Seen
Valid until: 10/30/2026
Sources
Related Entities
Related Claims
UnverifiedOn Windows, virtual memory can be configured to run MiniMax H3 when VRAM is insufficient.62% similarUnverifiedThe tool uses a local small model for transcription, available in two versions of 142 MB or 466 MB.62% similarUnverifiedIn v0.0.46, auto-compaction uses the context window of the selected model, and falls back correctly even if it is not provided in the directory entry.61% similarUnverifiedall-MiniLM-L6-v2 is an open-source sentence vector model with 384 dimensions, a model size of approximately 80 MB, and can complete single-item encoding on a standard CPU with millisecond-level latency.61% similarUnverifiedllama.cpp 0.3.0 leverages the unified memory feature via the --n-gpu-layers parameter, and on an M2 Max a 7B model can offload 35 layers.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1044659API
curl https://kongchang.com/api/v1/knowledge/claims/1044659MCP
get_claim(id=1044659)