Ernie GGUF models

118 GGUF models in the Ernie family, quantized by 52 uploaders. Sizes run from 11M to 300B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
ER
ERNIE Image Turbo
Ernie · unsloth
Params8.03B
Context—
Q4_K_M5.0 GB
GGUF
ER
Ernie-4.5-21B-A3B-Pt
Ernie · unsloth
Params21.8B
Context128K
Q4_K_M13.3 GB
GGUF
ER
Ernie-4.5-21B-A3B-Thinking
Ernie · unsloth
Params21.8B
Context128K
Q4_K_M13.3 GB
Reasoning
ER
ERNIE 4.5 21B A3B PT
Ernie · bartowski
Params21.8B
Context128K
Q4_K_M13.5 GB
GGUF
ER
ERNIE Image
Ernie · unsloth
Params8.03B
Context—
Q4_K_M5.0 GB
GGUF
ER
ERNIE 21B A3B Claude 4.5 High OPUS Thinking
Ernie · mradermacher
Params21.8B
Context128K
Q4_K_M13.2 GB
Reasoning
ER
ERNIE 4.5 0.3B PT
Ernie · bartowski
Params361M
Context128K
Q4_K_M0.2 GB
GGUF
ER
Ernie-4.5-0.3B-Pt
Ernie · unsloth
Params361M
Context128K
Q4_K_M0.2 GB
GGUF
ER
ERNIE 4.5 21B A3B PT
Ernie · lmstudio-community
Params21.8B
Context128K
Q4_K_M13.5 GB
GGUF
ER
ERNIE 4.5 21B A3B Thinking
Ernie · bartowski
Params21.8B
Context128K
Q4_K_M13.5 GB
Reasoning
ER
ERNIE 21B A3B Thinking Gemini 3 Pro High Reasoning V2
Ernie · mradermacher
Params21.8B
Context128K
Q4_K_M13.2 GB
Reasoning
ER
baidu.ERNIE 4.5 300B A47B PT
Ernie · DevQuasar
Params300B
Context128K
Q4_K_M180.2 GB
GGUF
ER
ERNIE 4.5 HUGE 51B A3B Thinking Brainstorm40x
Ernie · mradermacher
Params50.7B
Context128K
Q4_K_M30.7 GB
CodingReasoningTool use
ER
ERNIE Image Abliterated
Ernie · ponpoke
Params3.43B
Context256K
Q4_K_M2.1 GB
GGUF
ER
ERNIE 4.5 37B A3B Thinking Brainstorm20x
Ernie · mradermacher
Params37.2B
Context128K
Q4_K_M22.5 GB
CodingReasoningTool use
ER
ERNIE 4.5 21B A3B PT
Ernie · fernandoruiz
Params21.8B
Context128K
Smallest12.4 GB
GGUF
ER
ERNIE 4.5 21B A3B PT
Ernie · mradermacher
Params21.8B
Context128K
Q4_K_M13.2 GB
GGUF
ER
ERNIE 4.5 21B A3B Base PT
Ernie · mradermacher
Params22.1B
Context128K
Q4_K_M13.4 GB
GGUF
ER
ERNIE 4.5 0.3B PT
Ernie · mradermacher
Params361M
Context128K
Q4_K_M0.2 GB
GGUF
ER
ERNIE 4.5 21B A3B Thinking
Ernie · mradermacher
Params21.8B
Context128K
Q4_K_M13.2 GB
ReasoningTool use
ER
ERNIE 4.5 0.3B Base PT
Ernie · mradermacher
Params361M
Context128K
Q4_K_M0.2 GB
GGUF
ER
Ernie-4.5-21B-A3B-Thinking
Ernie · XythicK
Params21.8B
Context128K
Q4_K_M13.3 GB
ReasoningTool use
ER
Ernie-4.5-300B-A47B-Pt
Ernie · unsloth
Params299B
Context128K
Q4_K_M180.2 GB
GGUF
ER
ERNIE 4.5 29B A4B PT
Ernie · mradermacher
Params29B
Context128K
Q4_K_M17.5 GB
GGUF
ER
ERNIE 4.5 21B A3B Base PT
Ernie · mradermacher
Params22.1B
Context128K
Q4_K_M13.4 GB
GGUF
ER
Ernie 4.5 0.3b Aegis Safety Lora
Ernie · mradermacher
Params361M
Context128K
Q4_K_M0.2 GB
GGUF
ER
baidu.ERNIE 4.5 0.3B Base PT
Ernie · DevQuasar
Params361M
Context128K
Q4_K_M0.2 GB
GGUF
ER
ERNIE 21B A3B Claude 4.5 High OPUS Thinking
Ernie · mradermacher
Params21.8B
Context128K
Q4_K_M13.2 GB
ReasoningTool use
ER
ERNIE 4.5 0.3B PT
Ernie · lmstudio-community
Params361M
Context128K
Q4_K_M0.2 GB
GGUF
ER
ERNIE 4.5 HUGE 51B A3B Thinking Brainstorm40x
Ernie · mradermacher
Params50.7B
Context128K
Q4_K_M30.7 GB
CodingReasoningTool use

About the Ernie GGUF models

Ernie is represented on ggufmodels.com by 118 GGUF models, quantized by 52 uploaders on Hugging Face. The most downloaded are ERNIE Image Turbo, Ernie-4.5-21B-A3B-Pt and Ernie-4.5-21B-A3B-Thinking. Parameter counts run from 11M to 300B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Ernie model is between 0.2 to 181.8 GB, which is the quant most people start with. Most files come from mradermacher (28), ERNIE-Community (11) and unsloth (6). The quants you will meet most often are Q4_K_M (76), Q6_K (60), Q8_0 (59) and Q3_K_M (59), where the number is how many models offer that quant.

Frequently asked questions

Which Ernie GGUF should I download?

The most downloaded Ernie GGUF here is ERNIE Image Turbo. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Ernie model need?

Q4_K_M files of Ernie models on this site range from 0.2 to 181.8 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Ernie GGUF files come from?

The most common quantizers here are mradermacher, ERNIE-Community and unsloth. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing