AyaanAhmed123/Spark_one

Quantization vs unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit. unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit is a quantized version of the other (U8/BF16).

2 derivatives checked

• mradermacher/UltraThinker-Coder-3B-GGUF: LoRA-style
• mradermacher/Spark_one-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse