meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Parameters402B
Context–
Input → outputimage + text → text
Licenseother
PrecisionF8_E4M3 · fp8
ArchitectureLlama4ForConditionalGeneration
ReleasedApr 1, 2025
Downloads44.5K
Based on meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Other sizes and formats in the family
| Model | Params | Precision | Downloads |
|---|---|---|---|
| meta-llama/Llama-4-Maverick-17B-128E | 402B | BF16 | 314 |
| meta-llama/Llama-4-Maverick-17B-128E-Instruct | 402B | BF16 | 9.4K |
| meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8-Originalfp8 | 17B | – | 4 |
| meta-llama/Llama-4-Maverick-17B-128E-Instruct-Original | 17B | – | 10 |
| meta-llama/Llama-4-Maverick-17B-128E-Original | 17B | – | 7 |
Built on this model
| Model | Params | Precision | Downloads |
|---|---|---|---|
| meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8fp8 | 402B | F8_E4M3 | 44.5K |
| meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8-Originalfp8 | 17B | – | 4 |
This release in the news
No coverage of this exact release yet.