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 Aug 3, 2026ERNIE 4.5 VL is a large mixture-of-experts model from Baidu with downloadable weights under a permissive Apache licence. It accepts text and images, and carries 47 billion active parameters from a 423.5 billion total pool.
Pick this when you need a large multimodal model with genuinely open weights for commercial use, fine-tuning or redistribution. Use it if 123,000 tokens per request covers your context needs and you prefer hosted inference with an Apache licence. Skip it if you need verified quality scores, consistent throughput data across providers, or a busy hosting market with many offers to choose between.
The case for it
- Apache 2.0 licence allows commercial use, fine-tuning and redistribution on a 423.5-billion-parameter model.
- 47 billion active parameters from a 423.5 billion total pool, an activation ratio of about one in nine.
The case against it
- No measured benchmark scores in our data, so quality claims are unverified.
- Throughput data is sparse: only one of three tracked offers lists a speed figure, and the other two do not disclose.
- Only three current hosted offers, a thin market with limited provider choice.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up ERNIE 4.5 VL 424B A47B — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
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.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 3 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- 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 |
|---|---|---|---|---|---|---|
| OpenRouter | $0.42 / $1.25 | 123K | not measured | Unknown | Unknown | Unknown |
| Novita AI | $0.42 / $1.25 | 123K | not measured | Unknown | Unknown | Unknown |
| Novita AIfp16 | $0.42 / $1.25 | 123K | 34 tok/s | No | No | Confirmed |
Novita AIAcross the 3 listings we hold: 1 say they do not train on prompts, 0 say they do and 2 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✗ | ✗ | ✗ |
| Novita AI | |||
| Novita AIfp16 | ✗ | ✗ | ✗ |
Tool calling: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list. JSON output: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list. Strict schema: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list.
When we formed this view
Dates behind this page
Prices last checked 14h ago
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 board we watch has turned up a score, so we hold no quality figures at all.
- 1 of 3 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 3 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
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
- Modality record
- text+image->text
- Catalogue slug
- baidu-ernie-4-5-vl-424b-a47b