Meta-Llama-3.1-405B-Instruct-quantized.w8a16

RedHatAI/Meta-Llama-3.1-405B-Instruct-quantized.w8a16

Text Generation406B parametersLicense: llama3.1
Tracked by OpenModelStats since September 16, 2026View on Hugging Face ↗
Downloads 30D
106
Total downloads
2,331
Gained 7D
—
Gained 30D
—
Likes
2
Rank · tracked models
#53,849
399(down 399 places)this week
Parameters
406B
Last source update
Aug 19, 2026
Momentum
0.0
  • It moved from #16436 to #16597 among tracked Text Generation models this week.

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Overview

Meta-Llama-3.1-405B-Instruct-quantized.w8a16 is a text generation model published by RedHatAI. OpenModelStats has tracked the model since Sep 16, 2026, most recently observing it Sep 23, 2026.

Published
Aug 19, 2024
Last updated
Aug 19, 2026
Library
—
License
llama3.1
Task
Text Generation
Parameters
405,873,260,260
Spaces
—
Derivative models
—
Velocity 7D/day
—
safetensorsllamaint8vllmtext-generationconversationalendefritpthi

Publisher

RedHatAIView publisher statistics →

Derived from meta-llama/Llama-3.1-405B-Instruct (reported by the source; parent not yet tracked).

Similar models

Models similar to Meta-Llama-3.1-405B-Instruct-quantized.w8a16
ModelDL 30D
Llama-3.1-405B-FP8meta-llama456.5K
Llama-3.1-405B-Instruct-FP8meta-llama333
Llama-3.1-Tulu-3-405Ballenai340
Llama-3.1-405Bmeta-llama89.8K
Llama-3.1-405B-Instructmeta-llama12.3K
Llama-3.1-405B-Instruct-FP8nvidia6,455
RedHatAI/Meta-Llama-3.1-405B-Instruct-quantized.w8a16 — Downloads, Growth & Stats | OpenModelStats