Unverified50% confidenceFactExact time
Mazorca runs as follows: ollama pull gemma4:e4b-it-qat, git clone the repository then npm start, and access it at localhost:3000; the model can be swapped via the MAZORCA_MODEL environment variable, the Ollama default timeout is 180 seconds, and the Kestra flow is an optional component that is disabled by default.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedThe model gemma4:e2b-it-qat runs locally via Ollama on a CPU-only i5-1135G7 laptop, with a download size of 4.3 GB, a cold-start time of approximately 14 seconds, a warm-start time of 3.6 to 4.0 seconds, and a speed of approximately 15 to 20 tokens/second.66% similarUnverifiedPrefix caching for the Mamba architecture can now retain internal prefill checkpoints, with measured improvements of 9%–25% in time-to-first-token (TTFT) latency.57% similarUnverifiedgemma4-32K:26b-mlx can complete tasks but has excessively high memory usage and occasionally falls into infinite loops.57% similarUnverifiedOn an Apple M4 (16GB memory), running all-MiniLM-L6-v2 through ChromaDB embedded 50,000 documents in 161.6 seconds (309 per second), with no dedicated GPU required.55% similarUnverifiedLocal deployment does not equal data never leaving the premises: LM Studio server logs are kept on the Mac and fully store every answer from the model; CogniRunner execution logs store the first 300 characters of fields for each record and retain them for up to 30 days.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1033624API
curl https://kongchang.com/api/v1/knowledge/claims/1033624MCP
get_claim(id=1033624)