llama32_3bn_raft_v2 : GGUF

• For text only LLMs: llama-cli -hf tksoon/llama32_3bn_raft_v2 --jinja
• For multimodal models: llama-mtmd-cli -hf tksoon/llama32_3bn_raft_v2 --jinja

Available Model files:

• llama-3.2-3b-instruct.Q5_K_M.gguf
• llama-3.2-3b-instruct.Q8_0.gguf
• llama-3.2-3b-instruct.Q4_K_M.gguf

Ollama

An Ollama Modelfile is included for easy deployment. This was trained 2x faster with Unsloth