Open Issues Need Help
View All on GitHub small-Mac (16-32GB) reserve calibration — needs system_total_peak measurements (≥3 independent reporters) 14 days ago
help wanted good first issue measurement
click6067-ship-it/fitllm-engine click6067-ship-it/fitllm-engine Will this LLM fit your GPU or Mac? npx fitllm — accurate memory math for MLA/sliding-window/hybrid/MoE architectures that naive VRAM calculators get wrong by up to 18x. Single file, zero deps, conformance-vector tested. MIT.
Open project →
8
Will this LLM fit your GPU or Mac? npx fitllm — accurate memory math for MLA/sliding-window/hybrid/MoE architectures that naive VRAM calculators get wrong by up to 18x. Single file, zero deps, conformance-vector tested. MIT.
JavaScript
#amd#apple-silicon#cli#gguf#inference#kv-cache#llama-cpp#llm#local-llm#localllama#memory-calculator#mla#mlx#moe#nvidia#ollama#quantization#vram#vram-calculator#will-it-run
help wanted good first issue measurement
click6067-ship-it/fitllm-engine click6067-ship-it/fitllm-engine Will this LLM fit your GPU or Mac? npx fitllm — accurate memory math for MLA/sliding-window/hybrid/MoE architectures that naive VRAM calculators get wrong by up to 18x. Single file, zero deps, conformance-vector tested. MIT.
Open project →
8
Will this LLM fit your GPU or Mac? npx fitllm — accurate memory math for MLA/sliding-window/hybrid/MoE architectures that naive VRAM calculators get wrong by up to 18x. Single file, zero deps, conformance-vector tested. MIT.
JavaScript
#amd#apple-silicon#cli#gguf#inference#kv-cache#llama-cpp#llm#local-llm#localllama#memory-calculator#mla#mlx#moe#nvidia#ollama#quantization#vram#vram-calculator#will-it-run