Redhat

Llama-3.2-1B-Instruct-FP8 specs, VRAM requirements, and which GPUs can run it.

Llama-3.2-1B-Instruct-FP8-dynamic specs, VRAM requirements, and which GPUs can run it.

Meta-Llama-3.1-8B-Instruct-FP8 specs, VRAM requirements, and which GPUs can run it.

Qwen2.5-1.5B-quantized.w8a8 specs, VRAM requirements, and which GPUs can run it.