ERNIE 4.5 VL 424B A47B
Baidu · released Jun 28, 2025 · baidu/ERNIE-4.5-VL-424B-A47B-PT
- Type
- Open weightsApache License 2.0
- Params
- 424B
- Context
- 123K
47B active per word · about 92K words of context
Our take
Written Sep 4, 2026ERNIE 4.5 VL is Baidu's large vision-language model with downloadable weights under a permissive Apache licence. It handles text and images with 47 billion active parameters from a 423.5-billion-parameter mixture-of-experts architecture, though no benchmark scores are available to verify its quality.
Pick this for Apache-licensed multimodal workflows where you need image-plus-text input and a 123,000-token request limit. Use it if you want commercial freedom to fine-tune or redistribute a large MoE. Skip it if you need measured quality data, if output cost is your main constraint, or if you need consistent throughput guarantees.
The case for it
- Apache 2.0 licence allows commercial use, fine-tuning and redistribution on 423.5B total / 47B active weights.
- 47 billion active parameters with multimodal input support for vision-language tasks.
The case against it
- No benchmark scores in our data — no Elo, MMLU or other measured quality evidence.
- Premium output pricing with no verified performance level to justify it.
- Throughput data is thin: one endpoint reports 25 tokens per second, while two identically priced offers report none.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M3 Ultra (80-core GPU) · 512 GB
Room to spare. 107.3 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 2 hours ago — each listing carries its own date.
- per 1M tokens
- $0.42 in / $1.25 out
- Context served
- 123K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.42 / $1.25checked 2 hours ago | 123K | not measured | Unknown | Unknown | Unknown |
| Novita AIfp16Direct and through OpenRouter | $0.42 / $1.25checked 2 hours ago | 123K16K max reply through OpenRouter | 27 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
Novita AIAcross the 2 listings we hold: 1 says it does not train on prompts (only through OpenRouter), 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check (only through OpenRouter); the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✗ | ✗ | ✗ |
| Novita AIfp16Direct and through OpenRouter | ✗ | ✗ | ✗ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 0 of 2 listings say yes, 2 say no. Strict schema: 0 of 2 listings say yes, 2 say no.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts, and 1 answers only through OpenRouter, not for its own listing.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- baidu/ERNIE-4.5-VL-424B-A47B-PT
- Architecture
- Mixture of experts
- Takes in, gives back
- Text and images in, text out
- Catalogue slug
- baidu-ernie-4-5-vl-424b-a47b