sarvam-1.5-gguf : GGUF

• For text only LLMs: llama-cli -hf mashriram/sarvam-1.5-gguf --jinja
• For multimodal models: llama-mtmd-cli -hf mashriram/sarvam-1.5-gguf --jinja

Available Model files:

• QWEN35_FINAL_STITCHED.Q4_K_M.gguf
• QWEN35_FINAL_STITCHED.BF16-mmproj.gguf This was trained 2x faster with Unsloth