File	Quantization
Qwen3.5-2B-Opus46-Reasoning.Q2_K.gguf	Q2_K
Qwen3.5-2B-Opus46-Reasoning.Q3_K_M.gguf	Q3_K_M
Qwen3.5-2B-Opus46-Reasoning.Q4_0.gguf	Q4_0
Qwen3.5-2B-Opus46-Reasoning.Q4_K_M.gguf	Q4_K_M
Qwen3.5-2B-Opus46-Reasoning.Q5_0.gguf	Q5_0
Qwen3.5-2B-Opus46-Reasoning.Q5_K_M.gguf	Q5_K_M
Qwen3.5-2B-Opus46-Reasoning.Q6_K.gguf	Q6_K
Qwen3.5-2B-Opus46-Reasoning.Q8_0.gguf	Q8_0

Usage with llama.cpp

llama-cli -m Qwen3.5-2B-Opus46-Reasoning.Q4_K_M.gguf -p "What is 25 × 48?" --temp 0.6 -n 512

supersamdev/Qwen3.5-2B-Opus46-Reasoning-GGUF