Vram Python Packages

chimeraforge

PyPI capacity-planning CLI for LLM deployment. pip install chimeraforge.

canifinetune

Single-GPU LLM fine-tuning preflight: memory estimates, runnable LoRA/QLoRA recipes, and local measurements.

benchrig

Cross-platform benchmarking and hardware profiling rig for local LLMs across Ollama, Microsoft Foundry Local, ONNX Runtime GenAI, and Prism on Apple Silicon & CUDA.

localdeploy

Find, deploy, manage, and benchmark local AI models for your hardware across Ollama, llama.cpp, and compatible runtimes.

moe-fit

Will this mixture-of-experts model run on my machine, and how fast? Answered from the model's index, before downloading it.

glintbar

Live CPU, GPU, RAM, temperature and fan speeds in the unused gap of your Windows taskbar - always in view, never in the way, and no admin needed.

gpu-memory-guard

Check free NVIDIA VRAM before loading an AI model: a pre-load estimate with exit codes for scripts. On PyPI.

turboquant

First open-source TurboQuant KV cache compression for LLM inference. Drop-in for HuggingFace. pip install turboquant.

llm-sizer

Stop guessing GPU VRAM. CLI that sizes LLM weights + KV cache and picks the cheapest AWS GPU for vLLM, DeepSeek-R1, Llama 70B, and Qwen. JSON output for AI agents.

llm-neofetch-plus

LLM-Neofetch++ is an advanced system information tool designed specifically for local LLM (Large Language Model) usage. It provides detailed hardware detection with personalized recommendations for running AI models on your system.

llm-cal

LLM inference hardware calculator — architecture-aware (MLA/NSA/MoE), engine-aware (vLLM/SGLang), honest-labeled. Reads real safetensors bytes; supports 53 GPUs (NVIDIA / AMD / Huawei Ascend / 沐曦 / 昆仑芯 / 壁仞 / 寒武纪 / 海光).

gpu-quiescence

Train on the box you serve from: a VRAM readiness preflight for machines that serve and train on one GPU.

superclean-cli

An agentic-dev garbage collector for Windows, macOS, and Linux: a tiered RAM, VRAM, and disk cleanup ladder that never kills your active editors, terminals, or AI tools.

gpu-estimator

A Python package for estimating GPU memory requirements and the number of GPUs needed for training machine learning models

sparkfit

Memory capacity planner for running LLMs on the NVIDIA DGX Spark: unified-memory budgeting, bandwidth-aware decode-speed estimates, and a quantization advisor.

vrambatch

Run batched GPU work inside a VRAM budget, self-healing on CUDA out-of-memory

gemma4-adaptive-router

Adaptive dual-tier serving for Gemma 4 on consumer 16GB GPUs. Complexity + real-time VRAM routing between vLLM E4B and llama.cpp 27B. Production stack with OpenWebUI, monitoring, and more.

vram-check

Static VRAM estimator for PyTorch models: check GPU memory requirements before running training jobs

kvcache-bench

Benchmark every KV cache compression method on your GPU. One command, real numbers. Supports Ollama + llama.cpp.

quantsim-bench

Which quantization should I use? One command benchmarks every quant level on YOUR GPU.

spectral-kv

Up to 28x KV cache compression for LLMs via spectral SVD projection. Practically lossless on modern architectures.