ERNIE · Vision · ERNIE 4.5 VL
ERNIE 4.5 VL 28B-A3B Thinking is a current Vision release in the ERNIE family, certified from its immutable official source revision.
ERNIE 4.5 VL 28B-A3B Thinking is an official self-hostable Baidu release in the ERNIE Vision track. It uses Ernie4_5_VLMoeForConditionalGeneration, carries 28B / 3B 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 28B-A3B Thinking uses Ernie4_5_VLMoeForConditionalGeneration with 28B / 3B MoE. The stored architecture profile records 28 layers, hidden width 2560, 20 attention heads and a 131,072 token context ceiling where the official configuration publishes those fields.
Only exact, source-certified variants attached to this release are shown.
baidu/ERNIE-4.5-VL-28B-A3B-Thinking
Official · BF16 · safetensors
Runtime certified: Transformers vLLM Fastdeploy
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
Use only the listed transformers, vllm, 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.
Recommended best value
160 GB total VRAM · nvlink
74.91 GB headroom · Available
USD 1,830 / monthLowest-cost viable
96 GB total VRAM · pcie
10.91 GB headroom · Available
USD 1,000 / monthHighest performance
160 GB total VRAM · nvlink
74.91 GB headroom · Available
USD 1,830 / monthThe full 28B 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 28B-A3B Thinking 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.
ERNIE 4.5 VL 424B-A47B
Source revision: a88e2de785ab3000d4b7062ce96d896d2e36ecfa9c8940a9d2da110cc3fba3da
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Certified upstream runtime evidence is available for transformers, vllm, fastdeploy.
The stored commercial classification is Commercial Use Allowed. Consult the official apache-2.0 terms for the final obligations.
Last verified: 2026-09-03
