FitMyLLM
Baidu/Mixture of Experts

BaiduERNIE 4.5 VL 28B A3B Thinking

chatvisionreasoningmultilingual
28B
Parameters (3B active)
128K
Context length
0
Benchmarks
10
Quantizations
0
Architecture
MoE
Released
2025-11-11
Layers
28
KV Heads
4
Head Dim
128
Family
ernie

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q3_K_M4
15.1 GB
14.5 + 0.7 KV
low
Q3_K_L4.3
16.2 GB
15.5 + 0.7 KV
moderate
IQ4_XS4.46
16.8 GB
16.1 + 0.7 KV
moderate
Q4_K_S4.67
17.5 GB
16.8 + 0.7 KV
moderate
Q4_K_M4.89
18.3 GB
17.6 + 0.7 KV
good
Q5_K_S5.57
20.6 GB
20.0 + 0.7 KV
good
Q5_K_M5.7
21.1 GB
20.4 + 0.7 KV
good
Q6_K6.56
24.1 GB
23.4 + 0.7 KV
excellent
Q8_08.5
30.9 GB
30.2 + 0.7 KV
lossless
FP1616
57.1 GB
56.5 + 0.7 KV
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run ERNIE 4.5 VL 28B A3B Thinking now

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$# ERNIE 4.5 VL 28B A3B Thinking is not in Ollama's library, and we know no GGUF build of it

Search Hugging Face for a GGUF of it (https://huggingface.co/models?sort=trending&search=ERNIE-4.5-VL-28B-A3B-Thinking-PT+GGUF), or use the vLLM tab with the original weights.

Setup guide
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Apple M3 Pro (18GB)
18 GB VRAM • 150 GB/s
APPLE
$1599
NVIDIA RTX A4500
20 GB VRAM • 640 GB/s
NVIDIA
$2000
Apple M4 Pro (24GB)
24 GB VRAM • 273 GB/s
APPLE
$1399
NVIDIA L4 24GB
24 GB VRAM • 300 GB/s
NVIDIA
$2500
Apple M2 (24GB)
24 GB VRAM • 100 GB/s
APPLE
$999
Apple M3 (24GB)
24 GB VRAM • 100 GB/s
APPLE
$999
Apple M4 (24GB)
24 GB VRAM • 120 GB/s
APPLE
$699
NVIDIA Tesla M40 24 GB
24 GB VRAM • 288 GB/s
NVIDIA
NVIDIA Tesla P10
24 GB VRAM • 694 GB/s
NVIDIA
NVIDIA Tesla P40
24 GB VRAM • 347 GB/s
NVIDIA
NVIDIA RTX A5000
24 GB VRAM • 768 GB/s
NVIDIA
$2500

Find the best GPU for ERNIE 4.5 VL 28B A3B Thinking

Build Hardware for ERNIE 4.5 VL 28B A3B Thinking
Spec sheet

ERNIE 4.5 VL 28B A3B Thinking — 28B MoE.

Specifications
Parameters
28B (3B active)
Architecture
Mixture of Experts
Context Length
128K tokens
Capabilities
chat, vision, reasoning, multilingual
Release Date
2025-11-11
Provider
Baidu
Family
ernie
VRAM requirements
QuantBPWVRAMQuality
Q3_K_M414.5 GB88%
Q3_K_L4.315.5 GB90%
IQ4_XS4.4616.1 GB92%
Q4_K_S4.6716.8 GB93%
Q4_K_M4.8917.6 GB94%
Q5_K_S5.5720.0 GB96%
Q5_K_M5.720.4 GB96%
Q6_K6.5623.4 GB97%
Q8_08.530.2 GB100%
FP161656.5 GB100%
Compatible GPUs
30 @ Q4_K_M