Qwen3.5-4b-gas-CPT-SFT-gguf : GGUF

• For text only LLMs: llama-cli -hf Kadabra/Qwen3.5-4b-gas-CPT-SFT-gguf --jinja
• For multimodal models: llama-mtmd-cli -hf Kadabra/Qwen3.5-4b-gas-CPT-SFT-gguf --jinja

Available Model files:

• Qwen3.5-4b-gas-CPT.Q2_K_L.gguf
• Qwen3.5-4b-gas-CPT.Q8_0.gguf
• Qwen3.5-4b-gas-CPT.Q4_K_M.gguf
• Qwen3.5-4b-gas-CPT.BF16-mmproj.gguf This was trained 2x faster with Unsloth