ERNIE 4.5 VL 28B A3B PT — Hardware Requirements & GPU Compatibility
Vision
ERNIE 4.5 VL 28B A3B is Baidu's multimodal mixture-of-experts chat model, with 28 billion total parameters and 3 billion active per token. It handles text and images, supports both thinking and non-thinking modes, and uses a heterogeneous MoE design with separate text and vision experts (64 each, 6 activated, plus 2 shared). The PT suffix means the PyTorch Transformers weights, as opposed to the PaddlePaddle build. Because only 3 billion parameters are active, decoding is fast, though all weights must still be stored, so it fits a single 24 GB-class consumer GPU once quantized. The model supports a 131,072 token context window. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use. Published in June 2025, it belongs to the ERNIE 4.5 family, whose card also lists larger A47B MoE models.
30.7K downloads
104 likesSpecifications
- Publisher
- Baidu
- Family
- ERNIE
- Parameters
- 29.4B
- Architecture
- Ernie4_5_VLMoeForConditionalGeneration
- Context Length
- 131,072 tokens
- Vocabulary Size
- 103,424
- Release Date
- 2025-06-28
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does ERNIE 4.5 VL 28B A3B PT Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 59.2 GB | 66.6 GB | 58.80 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run ERNIE 4.5 VL 28B A3B PT?
BF16 · 59.2 GBERNIE 4.5 VL 28B A3B PT (BF16) requires 59.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 77+ GB is recommended. Using the full 131K context window can add up to 7.4 GB, bringing total usage to 66.6 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run ERNIE 4.5 VL 28B A3B PT?
BF16 · 59.2 GB22 devices with unified memory can run ERNIE 4.5 VL 28B A3B PT, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio (M3 Ultra, 96GB).
Runs great
— Plenty of headroom
Related Models
Frequently Asked Questions
- How much VRAM does ERNIE 4.5 VL 28B A3B PT need?
ERNIE 4.5 VL 28B A3B PT requires 59.2 GB of VRAM at BF16. Full 131K context adds up to 7.4 GB (66.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 29.4B × 16 bits ÷ 8 = 58.8 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 7.8 GB (at full 131K context)
VRAM usage by quantization
BF1659.2 GBBF16 + full context66.6 GB- Can NVIDIA GeForce RTX 5090 run ERNIE 4.5 VL 28B A3B PT?
No — ERNIE 4.5 VL 28B A3B PT requires at least 59.2 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run ERNIE 4.5 VL 28B A3B PT on a Mac?
ERNIE 4.5 VL 28B A3B PT requires at least 59.2 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run ERNIE 4.5 VL 28B A3B PT locally?
Yes — ERNIE 4.5 VL 28B A3B PT can run locally on consumer hardware. At BF16 quantization it needs 59.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is ERNIE 4.5 VL 28B A3B PT?
At BF16, ERNIE 4.5 VL 28B A3B PT can reach ~146 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 59.2 × 0.65 = ~370 tok/s
Estimated speed at BF16 (59.2 GB)
~370 tok/s~370 tok/s~291 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of ERNIE 4.5 VL 28B A3B PT?
At BF16, the download is about 58.80 GB.
- Which GPUs can run ERNIE 4.5 VL 28B A3B PT?
No single consumer GPU has enough VRAM to run ERNIE 4.5 VL 28B A3B PT at BF16 (59.2 GB). Multi-GPU or professional hardware is required.
- Which devices can run ERNIE 4.5 VL 28B A3B PT?
23 devices with unified memory can run ERNIE 4.5 VL 28B A3B PT at BF16 (59.2 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.