FrancescoBuda/Llama-ICD-coder-1B-merged

Quantization vs unsloth/Llama-3.2-1B-Instruct-bnb-4bit. unsloth/Llama-3.2-1B-Instruct-bnb-4bit is a quantized version of the other (BF16/U8).

1 derivatives checked

• mradermacher/Llama-ICD-coder-1B-merged-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse