DeepArch_v0.1-3B-GGZF-q4_k_m : GGUF

• For text only LLMs: llama-cli -hf DeepArch/DeepArch_v0.1-3B-GGZF-q4_k_m --jinja
• For multimodal models: llama-mtmd-cli -hf DeepArch/DeepArch_v0.1-3B-GGZF-q4_k_m --jinja

Available Model files:

• ministral-3-3b-reasoning-2512.Q4_K_M.gguf
• ministral-3-3b-reasoning-2512.BF16-mmproj.gguf This was trained 2x faster with Unsloth