- Source
- Model registry API
- Verified
- 19 Sep 2026
- Confidence
- High
01What this is
- Author
- baidu
- Family
- ERNIE 4.5
- Task
- vision-language
- Hugging Face
- baidu/ERNIE-4.5-VL-424B-A47B-PT
- OpenRouter
- baidu/ernie-4.5-vl-424b-a47b
- Also known as
- ERNIE 4.5 VL, ernie-4.5-vl, ernie, wenxin
02Registry facts
- LicenceFACT
apache-2.0
- FreshRetrieved 19 Sep 2026
- ParametersFACT
423.5B
- FreshRetrieved 19 Sep 2026
- Context lengthFACT
not returned by the registry
- Evidence not verified
- Downloads (30 days)FACT
538
- FreshRetrieved 19 Sep 2026
- LikesFACT
105
- FreshRetrieved 19 Sep 2026
- GatedFACT
no
- FreshRetrieved 19 Sep 2026
Model
- downloadsFACT
538
- Verification may be outdatedRetrieved 19 Sep 2026
- gatedFACT
false
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · NovitaFACT
123000
- Verification may be outdatedRetrieved 19 Sep 2026
- likesFACT
105
- Verification may be outdatedRetrieved 19 Sep 2026
- model licenseFACT
apache-2.0
- Verification may be outdatedRetrieved 19 Sep 2026
- parameter countFACT
423526285184
- Verification may be outdatedRetrieved 19 Sep 2026
Pricing
- hosted price completion per m · NovitaFACT
1.2500
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · NovitaFACT
0.4200
- AgeingRetrieved 19 Sep 2026
Other
- last modifiedFACT
2026-01-16T07:11:20.000Z
- Verification may be outdatedRetrieved 19 Sep 2026
- libraryFACT
transformers
- AgeingRetrieved 19 Sep 2026
03VRAM by quantisation
Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: 423.5B parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).
| Quantisation | Weights | Total |
|---|---|---|
| bf16bf16 is two bytes per weight, the same arithmetic as fp16. | 847.05 GB | 991.4 GB |
| fp8 | 423.53 GB | 504.34 GB |
| int4 | 211.76 GB | 260.81 GB |
What this estimate assumes
- Weights: 423.5B parameters × 2 bytes per parameter (fp16) = 847.05 GB.
- No model configuration was supplied, so the KV cache uses the size heuristic for this band: 0.459 MB per token, from extrapolated above 90B — no configuration was fetched for this band.
- KV cache: 0.459 MB per token × 8,192 tokens of context × 4 concurrent requests = 15.03 GB, sized for every user holding a full context at once.
- Overhead: 15% of weights plus KV cache for the runtime, activations and memory fragmentation = 129.31 GB.
- GB means 10⁹ bytes, matching how GPU memory is advertised.
- KV cache held at fp16 (2 bytes per element); quantising weights does not by itself quantise the cache.
- Peak figure, not average: prefix caching and paged attention usually keep real usage lower, while speculative decoding, CUDA graphs and a second resident model push it higher.
- "Concurrent" counts requests generated at the same instant, not people: 4 simultaneous requests is the worst case this estimate is built on — measure yours before buying.
04Hardware profiles
No hardware profile was sized for this answer.
05Hosted providers
- Prompt (per million tokens, USD)FACT
0.42
Source: openrouter
- FreshRetrieved 19 Sep 2026
- Completion (per million tokens, USD)FACT
1.25
- FreshRetrieved 19 Sep 2026
| Provider | Context |
|---|---|
| Novita | 123,000 |
06Deployment stacks
No published deployment stack names this model yet.
07Evidence
- 01–03Tier 4official repository / model cardOpenRouter
OpenRouter endpoints — baidu/ernie-4.5-vl-424b-a47b
https://openrouter.ai/api/v1/models/baidu/ernie-4.5-vl-424b-a47b/endpoints
AgeingRetrieved 19 Sep 2026sha256:ec76f559b3873 records · ·
- 04–10Tier 4official repository / model cardHugging Face Hub
Hugging Face model card data — baidu/ERNIE-4.5-VL-424B-A47B-PT
https://huggingface.co/api/models/baidu/ERNIE-4.5-VL-424B-A47B-PT
AgeingRetrieved 19 Sep 2026sha256:374aeca5c0aa7 records · · · · · ·
Improve this page
Sign in to contribute
From the field
0 deployments · 0 questions
Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.