Category
Local Model Models
Open-weight models with the smallest parameter counts that still run on consumer hardware.
3 models
← All categories
Top Local Model models
| Model | Pricing |
|---|---|
| LFM2.5-8B-A1B Liquid AI | Free |
| Qwen3.5-9B Qwen | $0.10/1M input |
| Gemma 4 26B A4B Google DeepMind | $0.06/1M input |
How these models were selected
Candidates have downloadable weights and comparatively modest active parameter counts, making quantized deployment on a workstation or small local server plausible.
When to use a different shortlist
Hardware fit depends on quantization, context length, batch size, and runtime. A model listed here may still exceed a laptop GPU at its best-quality settings.
Open each model page to verify current pricing, context limits, source links, and known limitations before choosing a provider.