Spec2LLM
Find the best LLMs for your hardware.
Detects your system specs (CPU, GPU, RAM, storage, OS) and recommends compatible LLMs ranked by performance fit. Works on Linux, Windows, and macOS — including Apple Silicon.
pip install spec2llm
spec2llm recommend
Quick Start
# See what models fit your system
spec2llm recommend
# Search for specific models
spec2llm search deepseek
# Compare two models
spec2llm compare llama-3.2-1b-q4 mistral-7b-q4
# Discover new models
spec2llm catalog update
# JSON output for scripting
spec2llm scan --json
Features
- Cross-platform hardware detection — CPU (cores, freq), GPU (NVIDIA VRAM, AMD, Apple Silicon), RAM, storage, OS
- Smart scoring — VRAM headroom (40%), RAM headroom (20%), GPU compute tier (20%), CPU cores (10%), Apple Silicon bonus (10%)
- Curated catalog — 40+ popular models (Llama 3.x, Mistral, Gemma, Qwen, DeepSeek, Phi, and more)
- Auto-discovery — Fetches new models from Ollama registry with estimated requirements
- Apple Silicon — Detects unified memory and adjusts scoring
- JSON output —
--jsonflag on all commands
Commands
| Command | Description |
|---|---|
spec2llm scan |
Detect and display all system hardware specs |
spec2llm recommend |
Find and rank best-matching LLMs |
spec2llm search <query> |
Search the model catalog |
spec2llm list |
Browse all models |
spec2llm install <model> |
Show install commands (Ollama, HuggingFace) |
spec2llm compare <a> <b> |
Compare two models vs your system |
spec2llm catalog update |
Fetch new models from Ollama registry |
How It Works
- Scan detects your CPU, RAM, GPU, storage, and OS
- Match filters models that fit your VRAM, RAM, and storage
- Score (0-100): VRAM headroom (40) + RAM headroom (20) + GPU tier (20) + CPU cores (10) + Apple Silicon bonus (10)
- Recommend returns a sorted table with scores
Requirements
- Python 3.9+
Platform Support
| Feature | Linux | Windows | macOS |
|---|---|---|---|
| CPU / RAM / Storage | ✅ | ✅ | ✅ |
| NVIDIA GPU (VRAM) | ✅ | ✅ | ❌ |
| AMD / Intel GPU | ✅ lspci | ✅ wmi | ❌ |
| Apple Silicon | N/A | N/A | ✅ |
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for spec2llm 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| spec2llm-0.1.0.tar.gz | 15.6 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| spec2llm-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 31.2 kB
Release files / spec2llm-0.1.0.tar.gz
| Download URL | spec2llm-0.1.0.tar.gz |
|---|---|
| Size | 15.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d268f58c5e0fd4d30877349c2a2b0e3dec590571d79b4ec05d7880c3a85cdd94
|
|
BLAKE2b-256 checksum How to use checksums |
00808a8bf8917f756c88195ed4ea09432aa2aa727d3d20b54e0a4f81b760d3be
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Release files / spec2llm-0.1.0-py3-none-any.whl
| Download URL | spec2llm-0.1.0-py3-none-any.whl |
|---|---|
| Size | 15.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
80b8a930577038388031809762fedf0443fd17f052bf39b06a9ef3ea81bb094c
|
|
BLAKE2b-256 checksum How to use checksums |
6ed02089626078c6a952417e5933422c8e947f4fbbe801ad0da81d4f8bcb723d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Security for spec2llm 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
