ERNIE-4.5-VL-424B-A47B-Paddle
baidu/ERNIE-4.5-VL-424B-A47B-Paddle
Official · BF16 · safetensors
Runtime certified: Fastdeploy
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
ERNIE · Vision · ERNIE 4.5 VL
ERNIE 4.5 VL 424B-A47B: Specs, GPU requirements, hosting & deployment
ERNIE 4.5 VL 424B-A47B is a current Vision release in the ERNIE family, certified from its immutable official source revision.
Total parameters424.0B
Active parameters47.0B
Context window131,072 tokens
Release statusCurrent · Current
ArchitectureErnie4_5_VLMoeForConditionalGeneration
ModalitiesMultimodal
Licenseapache-2.0
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed
Release date2025-06-28
Architecture, strengths and use cases
ERNIE 4.5 VL 424B-A47B is an official self-hostable Baidu release in the ERNIE Vision track. It uses Ernie4_5_VLMoeForConditionalGeneration, carries 424B / 47B MoE, supports a verified context window of 131,072 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
ERNIE 4.5 VL 424B-A47B uses Ernie4_5_VLMoeForConditionalGeneration with 424B / 47B MoE. The stored architecture profile records 54 layers, hidden width 8192, 64 attention heads and a 131,072 token context ceiling where the official configuration publishes those fields.
Verified Ernie4_5_VLMoeForConditionalGeneration architecture
131,072 token certified context
Official BF16, Unknown checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Recommended hardware
Use only the listed fastdeploy runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
Estimated weight memory813.45 GB
KV cache1.69 GB
Runtime overhead203.37 GB
Total with safety margin1262.95 GB
Technically compatible reference sizing
No current FusionPointAI inventory passes every runtime, architecture, topology and memory gate for this exact checkpoint. Use the estimator for global compatible hardware.
License and self-hosting considerations
The full 424B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
ERNIE 4.5 VL 424B-A47B is published under apache-2.0. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed. The official license permits commercial use; its obligations still apply.
Alternatives and sibling variants
ERNIE 4.5 VL 28B-A3B Thinking
Release timeline
baidu/ernie/ernie-4-5-vl-424b-a47b @ e380d6af32ddccfb49168a08181655f6c7e4472dc055a88b78d29f8f5e63bdd1
Frequently asked questions
How much VRAM does ERNIE 4.5 VL 424B-A47B require?
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Which runtimes support ERNIE 4.5 VL 424B-A47B?
Certified upstream runtime evidence is available for fastdeploy.
Can ERNIE 4.5 VL 424B-A47B be used commercially?
The stored commercial classification is Commercial Use Allowed. Consult the official apache-2.0 terms for the final obligations.
Official references
Last verified: 2026-09-03