ER

Ernie-4.5-300B-A47B-Pt

ErnieGGUF by unslothUpdated 2025-07-18
Download on Hugging Face
Parameters299B
Context128K
Layers54
Architectureernie4_5-moe
Smallest quant76.8 GB
Quick answer

Ernie-4.5-300B-A47B-Pt needs about 182.5 GB of memory at Q4_K_M (a 180.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 27 quants, from 76.8 GB (TQ1_0) to 599.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 7.2 GB.

Ernie-4.5-300B-A47B-Pt is a 299B-parameter Ernie model in GGUF format, quantized by unsloth. Its trained context length is 128K tokens. The repository has 27 quant files, from 76.8 GB (TQ1_0) to 599.0 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_076.8 GB 79.1 GB
Too big Get file →
IQ1_S86.5 GB (2 parts) 88.8 GB
Too big Get file →
IQ1_M93.2 GB (2 parts) 95.5 GB
Too big Get file →
IQ2_XXS101.3 GB (3 parts) 103.6 GB
Too big Get file →
IQ2_M105.7 GB (3 parts) 108.0 GB
Too big Get file →
Q2_K109.1 GB (3 parts) 111.4 GB
Too big Get file →
Q2_K_L109.3 GB (3 parts) 111.6 GB
Too big Get file →
Q2_K_XL114.6 GB (3 parts) 116.9 GB
Too big Get file →
IQ3_XXS125.2 GB (3 parts) 127.5 GB
Too big Get file →
Q3_K_S129.1 GB (3 parts) 131.4 GB
Too big Get file →
Q3_K_XL134.4 GB (3 parts) 136.7 GB
Too big Get file →
Q3_K_M142.6 GB (3 parts) 144.9 GB
Too big Get file →
IQ4_XS159.5 GB (4 parts) 161.9 GB
Too big Get file →
IQ4_NL168.8 GB (4 parts) 171.1 GB
Too big Get file →
Q4_0169.2 GB (4 parts) 171.5 GB
Too big Get file →
Q4_K_S169.6 GB (4 parts) 171.9 GB
Too big Get file →
Q4_K_XL172.6 GB (4 parts) 175.0 GB
Too big Get file →
Q4_K_M180.2 GB (4 parts) 182.5 GB
Too big Get file →
Q4_1187.4 GB (4 parts) 189.8 GB
Too big Get file →
Q5_K_S206.1 GB (5 parts) 208.4 GB
Too big Get file →
Q5_K_M212.0 GB (5 parts) 214.3 GB
Too big Get file →
Q5_K_XL214.0 GB (5 parts) 216.3 GB
Too big Get file →
Q6_K245.8 GB (5 parts) 248.1 GB
Too big Get file →
Q6_K_XL257.0 GB (6 parts) 259.3 GB
Too big Get file →
Q8_0318.3 GB (7 parts) 320.6 GB
Too big Get file →
Q8_K_XL347.8 GB (8 parts) 350.1 GB
Too big Get file →
BF16599.0 GB (13 parts) 601.3 GB
Too big Get file →

What GPU do you need for Ernie-4.5-300B-A47B-Pt?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Ernie-4.5-300B-A47B-Pt quant should you choose?

Q4_K_M is the usual starting point for Ernie-4.5-300B-A47B-Pt: it balances file size and quality well. Here it is a 180.2 GB file.

The Q8_0 file is 318.3 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is TQ1_0 at 76.8 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureernie4_5-moe
Parameters299B (approximate, mixture of experts)
Active parameters47B
Layers54
Trained context131,072 tokens
KV cache (fp16)216 KB per token

Source

Quantized byunsloth
FamilyErnie
Licenseapache-2.0
Downloads (HF)539
Last updated2025-07-18

Frequently asked questions about Ernie-4.5-300B-A47B-Pt

How much VRAM does Ernie-4.5-300B-A47B-Pt need?

About 182.5 GB at Q4_K_M with an 8K context window. That is the 180.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Ernie-4.5-300B-A47B-Pt on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 79.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ernie-4.5-300B-A47B-Pt GGUF?

It depends on the quant: TQ1_0 is 76.8 GB, IQ1_S is 86.5 GB, IQ1_M is 93.2 GB, IQ2_XXS is 101.3 GB, IQ2_M is 105.7 GB, Q2_K is 109.1 GB and 21 more.

What context length does Ernie-4.5-300B-A47B-Pt support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.8 GB at 8K and 7.2 GB at 32K.

Where can I download Ernie-4.5-300B-A47B-Pt GGUF?

The files are on Hugging Face in the unsloth/ERNIE-4.5-300B-A47B-PT-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Ernie-4.5-300B-A47B-Pt use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of ERNIE-4.5-300B-A47B-PT

Similar models

Browse all →

More from unsloth

All by unsloth →

More Ernie models

All Ernie →

Other large models

All large models →