Wan GGUF models

243 GGUF models in the Wan family, quantized by 181 uploaders. Sizes run from 34M to 17.3B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
WA
Wan2.1
Wan · DeepBeepMeep
Params9.2B
Context256K
Q4_K_M0.3 GB
GGUF
WA
Wan2.2 I2V A14B
Wan · QuantStack
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
WA
Wan2.2 TI2V 5B
Wan · QuantStack
Params5B
Context—
Q4_K_M3.4 GB
GGUF
WA
Wan2.2 TI2V 5B
Wan · unsloth
Params5B
Context—
Q4_K_M3.4 GB
GGUF
WA
Wan2.2 Animate 14B
Wan · QuantStack
Params17.3B
Context—
Q4_K_M11.5 GB
GGUF
WA
Wan2.2 T2V A14B
Wan · QuantStack
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
WA
Wan2.1 I2V 14B 480P
Wan · city96
Params16.4B
Context—
Q4_K_M11.3 GB
GGUF
WA
Wan2.2 I2V A14B
Wan · bullerwins
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
WA
Wan2.1 14B VACE
Wan · QuantStack
Params17.3B
Context—
Q4_K_M11.6 GB
GGUF
WA
LiveAvatar
Wan · audio-cpp
Params16.3B
Context—
Smallest0.3 GB
GGUF
WA
Wan2.2 S2V 14B
Wan · QuantStack
Params16.3B
Context—
Q4_K_M13.9 GB
GGUF
WA
WAN2.2 I2V A14B DISTILL LIGHTX2V 4STEP
Wan · jayn7
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
WA
Wan2.2BasedModels
Wan · Isi99999
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
WA
Wan2.2 TI2V 5B Turbo
Wan · hum-ma
Params5B
Context—
Q4_K_M3.4 GB
GGUF
WA
Wan Animate 2 GGUFs
Wan · realrebelai
Params16.4B
Context—
Q4_K_M11.3 GB
GGUF
WA
Wan2.1 T2V 14B
Wan · city96
Params14.3B
Context—
Q4_K_M10.1 GB
GGUF
WA
wan 1.3b
Wan · calcuis
Params127M
Context—
Q4_K_M1.0 GB
GGUF
WA
WAN2.2 14B Rapid AllInOne GGUF NSFW v10
Wan · desirel
Params16.4B
Context—
Q4_K_M10.8 GB
GGUF
WA
Wan2.1 FLF2V 14B 720P
Wan · city96
Params16.4B
Context—
Q4_K_M11.3 GB
GGUF
WA
Wan2.2 VACE Fun A14B
Wan · QuantStack
Params17.3B
Context—
Q4_K_M11.6 GB
GGUF
WA
Wan2.1 I2V 14B 720P
Wan · city96
Params16.4B
Context—
Q4_K_M11.3 GB
GGUF
WA
Wan2.2 Fun A14B Control Camera
Wan · QuantStack
Params14.8B
Context—
Q4_K_M10.7 GB
GGUF
WA
Wan2.2 Fun A14B Control
Wan · QuantStack
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
WA
Wan2.2 T2V A14B
Wan · bullerwins
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
WA
Wan2.1 T2V 1.3B
Wan · samuelchristlie
Params1.42B
Context—
Q4_K_M1.0 GB
GGUF
WA
Wan2.2 LightX2V 260412 4STEP
Wan · Abiray
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
WA
WAN2.2 14B Rapid AllInOne GGUF NSFW v10
Wan · DoorZekor
Params16.4B
Context—
Q4_K_M10.8 GB
GGUF
WA
Wan2.2 Fun A14B InP
Wan · QuantStack
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
WA
NSFW Wan 14b
Wan · NSFW-API
Params14.3B
Context—
Smallest9.7 GB
GGUF
WA
Wan2.2 Fun 5B Control
Wan · QuantStack
Params5B
Context—
Q4_K_M3.4 GB
GGUF

About the Wan GGUF models

Wan is represented on ggufmodels.com by 243 GGUF models, quantized by 181 uploaders on Hugging Face. The most downloaded are Wan2.1, Wan2.2 I2V A14B and Wan2.2 TI2V 5B. Parameter counts run from 34M to 17.3B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Wan model is between 0.2 to 16.8 GB, which is the quant most people start with. Most files come from QuantStack (20), vantagewithai (6) and city96 (6). The quants you will meet most often are Q8_0 (139), Q4_K_M (123), Q6_K (121) and Q5_K_M (103), where the number is how many models offer that quant.

Frequently asked questions

Which Wan GGUF should I download?

The most downloaded Wan GGUF here is Wan2.1. 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 Wan model need?

Q4_K_M files of Wan models on this site range from 0.2 to 16.8 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 Wan GGUF files come from?

The most common quantizers here are QuantStack, vantagewithai and city96. 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