SmolLM2-360M-Instruct-q4f16_1 (~0.4 GB)
Qwen2.5-0.5B-Instruct-q4f16_1 (~0.5 GB)
Llama-3.2-1B-Instruct-q4f16_1 (~0.9 GB)
Llama-3.2-3B-Instruct-q4f16_1 (~2.3 GB)
Load model
Clear chat
Pick a model and click Load. It downloads once, then is cached.
Send