Llama 3.3 70B Instruct Quantized - a RedHatAI Collection

RedHatAI 's Collections

Red Hat AI validated models - v1.0

Gemma-3 Quantized

Whisper Quantized

Llama 4 Quantized

Qwen3 Quantized

Mistral-Small-3.1 (2503) Instruct Quantized

Phi-4 Quantized

Llama 3.3 70B Instruct Quantized

Qwen 2.5 Quantized

Granite Quantized

Llama 3.3 70B Instruct Quantized

updated 1 day ago

Quantized variants of Meta Llama 3.3 multilingual large language model (LLM) is an instruction tuned generative model in 70B (text in/text out).

RedHatAI/Llama-3.3-70B-Instruct-quantized.w8a8

Text Generation • 71B • Updated May 30 • 37.7k • 10
RedHatAI/Llama-3.3-70B-Instruct-FP8-dynamic

Text Generation • 71B • Updated May 30 • 9.52k • 9
RedHatAI/Llama-3.3-70B-Instruct-quantized.w4a16

Text Generation • 11B • Updated May 30 • 9.4k • 1