llmfit

LLmfit is a terminal tool that detects hardware and recommends open-source large language models.

Llmfit inspects CPU, system RAM, GPUs, VRAM, and accelerators to determine which open-source large language models run comfortably on a machine. It analyzes parameter counts, context lengths, and quantization formats like GGUF, AWQ, GPTQ, and EXL2 to project memory footprints and tokens-per-second performance. The tool features an interactive terminal user interface, a classic CLI mode, and a web dashboard with HTTP JSON endpoints. It supports multi-GPU setups, MoE architectures, and local runtime providers such as Ollama, llama.cpp, MLX, Docker Model Runner, and LM Studio. Users can also download models, benchmark real token speeds, and share results back to the project.

llmfit at a glance

Best for: Software engineer
Runs on: macOS, Linux, Windows, Web, CLI, API, self-hosted, open source
Pricing: Free and open source under the MIT license
Released: February 2026
Category: AI coding tool
Website: github.com/AlexsJones/llmfit

Key features

Hardware auto-detection for CPU, RAM, and GPUs
Model compatibility engine for parameter and memory analysis
Interactive TUI and web dashboard
REST API endpoints for system and model data
Local runtime provider integration
Community benchmark sharing

Use it for

Find open-source LLMs compatible with local hardware
Benchmark token generation speed on local machines
Integrate model recommendations into automated deployment pipelines
Simulate hardware performance for different model configurations

Alternatives to llmfit

llmrun — Check which open models run on your specific GPU or Mac instantly.
whichllm — Ranks models using real benchmarks and hardware fit instead of parameter count.
AirLLM — Runs massive 70B+ parameter models on small 4GB consumer GPUs.
llm-d — Deploys production-grade LLM serving on existing hardware clusters.
LMDeploy — Accelerates inference with high-performance engines and quantization tools.
MLX LM — Runs LLMs and fine-tuning natively on Apple silicon hardware.
LLM CLI — It enables command-line interaction with remote APIs and local machine models.
MLC LLM — Enables native optimization and deployment of AI models across platforms.
LiteLLM — One OpenAI-format API for 100+ LLM providers
Soup — Fine-tune and align models like Llama-3.1-8B on a 4 GB laptop GPU.
LlamaFactory — Provides a code-free CLI and Web UI for training 100+ different LLMs.
MTPLX — It runs local models twice as fast via native MTP speculative decoding.

All llmfit alternatives