Llama-4-Maverick-17B-128E-Instruct-FP8
Support summary
Llama-4-Maverick-17B-128E-Instruct-FP8 is a checkpoint published by Meta, built on the Llama4ForConditionalGeneration architecture. vLLM 0.28.0, the newest indexed vLLM release, documents support. TensorRT-LLM lists its architecture, but not this exact checkpoint.
vLLM documents support in 20 of 20 indexed releases, from 0.17.0 to 0.28.0.
- License
- llama4
Hugging Face model card
- Publisher
- Meta
- Task
- image text to text
- License
- llama4
- Library
- transformers
- Architecture
- Llama4ForConditionalGeneration
- Weight tensor elements
- 401.6B
- Tensor types
- BF16, F8_E4M3
- Languages
- ar, de, en, es, fr, hi, id, it, pt, th, tl, vi
- Base models
- meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
- Weight access
- Publisher approval or terms required
- Repository created
- 2025-04-01
Model notes and sources
The FP8 checkpoint is distinct from its unquantized sibling; architecture support alone does not validate precision.
- vLLM v0.28.0 · docs/models/supported_models.md · 20 indexed revisions, v0.17.0 to v0.28.0
- meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 publisher metadata
- meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 · publisher model card
- meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 · Hugging Face metadata
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | 0.28.0Newest indexed | Checkpoint evidenceSource: vLLM v0.28.0 · docs/models/supported_models.mdReviewed | 0.28.0This release | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | 0.5.19Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | Architecture listed; exact checkpoint unknown | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||