llmfit scans your hardware and tells you exactly which local LLMs will actually run
thisdudelikesAI · x · 2026-11-16
llmfit is an open-source CLI that scans your RAM, CPU, GPU and VRAM, then scores hundreds of models (Meta, Mistral, Qwen, DeepSeek and more) across four dimensions: quality (parameter count and quantization), estimated tokens/sec for your exact backend, memory fit, and context window support. Each model gets a Perfect/Good/Marginal/Too Tight label, the tool auto-picks the best quantization by stepping down until it fits, and it works out of the box with Ollama, llama.cpp, MLX and LM Studio.
More from Infra
- DeepSeek V4 Pro fingerprint change is just a cluster swap: weights bit-identical, likely Ascend backend — teortaxesTex · 2026-11-16
- Rumor: DeepSeek V5 in pretraining, ~2T-param sparse MoE trained entirely on Huawei Ascend, no NVIDIA — DeryaTR_ · 2026-11-16
- Microsoft email outage delayed chlorine alerts at German theme park hotel, 15 guests harmed — evilsocket · 2026-11-16
- How Lisa Su took AMD from near-bankruptcy to $1T — and she's Jensen Huang's cousin — bigaiguy · 2026-11-16
- tandem.cpp v0.3.0: 2-6x Faster Prompt Processing, DeepSeek-V4.1 GGUFs Supported — smflx · 2026-11-16
- SemiAnalysis reportedly cuts 2028 AI accelerator capex forecast by 28% — firstadopter · 2026-11-16