fitllm-engine
MITAccurate local-LLM memory math — will this model fit your GPU or Mac? Models sliding-window, hybrid/linear, MLA compressed-KV and MoE architectures that naive VRAM calculators get wrong by up to ~18x. Zero deps, single file, conformance-vector tested.
100
Security score
0 known advisories in v2.6.0
Weekly downloads
—
Unpacked size
99.9 kB
Dependencies
0
Last publish
17 days ago
Security advisories
No known vulnerabilities affect v2.6.0.