ERNIE 4.5 VL 424B A47B
Baiduhuggingface.co/baidu/ERNIE-4.5-VL-424B-A47B-PT
ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...
Updated 1 h ago · first seen 11 Sept 2026
model_01M294WWF5JK3S3G69TDNAY05Z
- Parameters
- 423.5B · 47B active
- T2 · 1 h ago
- Context
- 123K tokens
- T2 · 1 h ago
- Released
- 28 Jun 2025
- T2 · 1 h ago
- License
- apache-2.0
- T2 · 1 h ago
- Knowledge cutoff
- Mar 2025
- T2 · 1 h ago
Specification
- Release date
- 28 Jun 2025
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- License
- apache-2.0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Architecture
- Ernie4_5_VLMoeForConditionalGeneration
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Parameters
- 423.5B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Active parameters
- 47B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Context window
- 123K tokens
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Max output
- 16K tokens
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Knowledge cutoff
- Mar 2025
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Modalities
- image, text
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Input modalities
- image, text
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Languages
- en, zh
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- File size
- 847.2 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Hugging Face repo
- baidu/ERNIE-4.5-VL-424B-A47B-PT
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Pipeline tag
- image-text-to-text
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Downloads
- 460
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Likes
- 105
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Last modified
- 2026-01-16T07:11:20+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Downloads all time
- 325,197
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Model type
- ernie4_5_moe_vl
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Openrouter id
- baidu/ernie-4.5-vl-424b-a47b
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Supported parameters
- frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, repetition_penalty, seed, stop, temperature, top_k, top_p
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Tags
- transformers, safetensors, ernie4_5_moe_vl, image-text-to-text, ERNIE4.5, custom_code, en, zh
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Weights dtype
- BF16, F16, F32
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
33
Source tiers
T233
Freshest observation
1 h ago
Conflicts
None
Modalities
- Modalities
- imagetext
- Input
- imagetext
- Output
- text
Capabilities
Tool calling
No
OpenRouter public model & pricing listing · T2
Structured output
No
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Yes
OpenRouter public model & pricing listing · T2
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 123K tokens
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Max output
- 16K tokens
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Knowledge cutoff
- Mar 2025
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Languages
- en, zh
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
No benchmark results recorded
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| OpenRouterbaidu/ernie-4.5-vl-424b-a47b | $0.42 | $1.25 | — | — | 123K | 1 h ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- OpenRouter
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| Apple M3 Ultra | 4bit | — | 244.0 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 244.0 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 244.0 GB | No |
| Apple M2 Ultra | 4bit | — | 244.0 GB | No |
| NVIDIA B200 | 4bit | 180 GB | 244.0 GB | No |
| NVIDIA H200 | 4bit | 141 GB | 244.0 GB | No |
| Apple M1 Ultra | 4bit | — | 244.0 GB | No |
| Apple M3 Max | 4bit | — | 244.0 GB | No |
| Apple M4 Max | 4bit | — | 244.0 GB | No |
| NVIDIA DGX Spark | 4bit | 128 GB | 244.0 GB | No |
| Apple M2 Max | 4bit | — | 244.0 GB | No |
| NVIDIA A100 80GB | 4bit | 80 GB | 244.0 GB | No |
| NVIDIA H100 SXM | 4bit | 80 GB | 244.0 GB | No |
| Apple M1 Max | 4bit | — | 244.0 GB | No |
| Apple M4 Pro | 4bit | — | 244.0 GB | No |
| Apple M3 Pro | 4bit | — | 244.0 GB | No |
| Apple M1 Pro | 4bit | — | 244.0 GB | No |
| Apple M2 Pro | 4bit | — | 244.0 GB | No |
| Apple M4 | 4bit | — | 244.0 GB | No |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 244.0 GB | No |
| Apple M2 | 4bit | — | 244.0 GB | No |
| Apple M3 | 4bit | — | 244.0 GB | No |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 244.0 GB | No |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 244.0 GB | No |
| Apple M1 | 4bit | — | 244.0 GB | No |
No lineage recorded
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Downloads all time
Downloads all timemetric.downloads_all_time1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 325,197 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
ERNIE 4.5 VL 424B A47B: release date changed from 2025-06-30 to 2025-06-28
Release date30 Jun 2025→28 Jun 2025huggingfaceOpenRouter lists ERNIE 4.5 VL 424B A47B at $0.42 in / $1.25 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/baidu/ERNIE-4.5-VL-424B-A47B-PT/raw/main/README.md | model_card | T2· Quality secondary | 11 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/baidu/ERNIE-4.5-VL-424B-A47B-PT | model_page | T2· Quality secondary | 1 h ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=baidu&p=0&sort=downloads | listing | T2· Quality secondary | 1 h ago | 2 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 1 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.