udgamlabs/Udgam-384M-Chat

Text Generation • 0.4B • Updated about 14 hours ago • 539

Note Start here. Turns requests into app function calls, fills JSON from documents and proposes shell commands. 4,096-token context.

udgamlabs/Udgam-384M-Chat-GGUF

Text Generation • 0.4B • Updated about 14 hours ago • 208 • 1

Note GGUF files for Ollama, LM Studio and llama.cpp. Q8_0 by default, Q4_K_M (238 MB) for phones.

udgamlabs/Udgam-384M-Chat-MLX

Text Generation • 0.4B • Updated about 14 hours ago • 570 • 1

Note MLX fp16 for Apple silicon (mlx-lm).

udgamlabs/Udgam-384M-Chat-MLX-4bit

Text Generation • 0.4B • Updated about 14 hours ago • 49

Note MLX 4-bit for Apple silicon: the smallest download.

udgamlabs/Udgam-384M-Base-4K

Text Generation • 0.4B • Updated about 14 hours ago • 571

Note Base model with a 4,096-token context. Udgam-384M-Chat was fine-tuned from it. Continues text; not instruction-tuned.

udgamlabs/Udgam-384M-Base

Text Generation • 0.4B • Updated 4 days ago • 570

Note The original base model, 2,048-token context. Continues text; not instruction-tuned.