IQ2_XXS GGUF models

Importance-matrix 2-bit quant. Extreme compression with a large quality cost. 26647 models have a IQ2_XXS file. Sizes run from 2M to 2780B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.8-27B
Qwen · unsloth
Params27.3B
Context256K
Q4_K_M16.5 GB
Vision
QW
Qwen3.8 27B
Qwen · byteshape
Params27.3B
Context256K
Smallest8.8 GB
Vision
DE
DeepSeek V4.1 Flash 1017 GSQ RCO
DeepSeek · ISTA-DASLab
Params197B
Context—
Smallest110.6 GB
GGUF
QW
Qwen3.5-9B
Qwen · unsloth
Params8.95B
Context256K
Q4_K_M5.7 GB
Vision
QW
Qwen3.6-35B-A3B
Qwen · unsloth
Params34.7B
Context256K
Q4_K_M22.1 GB
Vision
QW
Qwen3.6-35B-A3B
Qwen · unsloth
Params35.5B
Context256K
Q4_K_M22.7 GB
Vision
QW
Qwen3.5-4B
Qwen · unsloth
Params4.21B
Context256K
Q4_K_M2.7 GB
Vision
DE
DeepSeek V4.1 Flash Vision Encoder
DeepSeek · antirez
Params1400B
Context—
Smallest1.0 GB
GGUF
GE
Gemma-4-26B-A4B-It
Gemma · unsloth
Params25.2B
Context256K
Q4_K_M16.9 GB
Vision
QW
Qwen3.8 Flash Next Uncensored
Qwen · orcarouter
Params177B
Context256K
Q4_K_M119.2 GB
ReasoningTool useVision
QW
Qwen3.5-35B-A3B
Qwen · unsloth
Params34.7B
Context256K
Q4_K_M22.0 GB
Vision
QW
Qwen2.5 32B Instruct
Qwen · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
GGUF
CY
Cyber Ornith 1.5 9B OBLITERATED
Cyber · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
GL
GLM 5.3 Flash
GLM · unsloth
Params320B
Context1024K
Smallest93.1 GB
Vision
MU
Muse Glimmer 30B
Muse · unsloth
Params27.9B
Context128K
Smallest1.6 GB
Vision
IN
Inkling-Small
Inkling · unsloth
Params264B
Context1024K
Q4_K_M162.5 GB
ReasoningVision
QW
Swift Qwen3.8 27b
Qwen · ukisai
Params27.3B
Context256K
Q4_K_M18.0 GB
ReasoningVision
GL
GLM 5.3 Flash Maya
GLM · peasantsmith
Params370B
Context64K
Smallest0.0 GB
Vision
QW
Qwen3-4B
Qwen · unsloth
Params4B
Context40K
Q4_K_M2.5 GB
GGUF
GL
orcarouter GLM 5.3 Flash Uncensored
GLM · BoldingBuilds
Params321B
Context1024K
Smallest97.1 GB
Vision
QW
Qwen3-Coder-30B-A3B-Instruct
Qwen · unsloth
Params30.5B
Context256K
Q4_K_M18.6 GB
Coding
QW
Qwen3-4B-Instruct-2507
Qwen · unsloth
Params4B
Context256K
Q4_K_M2.5 GB
GGUF
QW
Qwen3.5-2B
Qwen · unsloth
Params1.88B
Context256K
Q4_K_M1.3 GB
Vision
QW
Qwen3-Vl-4B-Instruct
Qwen · unsloth
Params4B
Context256K
Q4_K_M2.5 GB
Vision
QW
Qwen3-30B-A3B-Instruct-2507
Qwen · unsloth
Params30.5B
Context256K
Q4_K_M18.6 GB
GGUF
BI
BigBang v1
Bigbang · bartowski
Params35.5B
Context256K
Q4_K_M21.9 GB
Vision
QW
Qwen3.6-27B
Qwen · unsloth
Params27B
Context256K
Q4_K_M16.8 GB
Vision
TH
Thomson 1.0 Small
Thomson · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
Vision
KI
Kimi-K3
Kimi · unsloth
Params2780B
Context1024K
Smallest466.4 GB
Vision
KA
KAT Coder V2.5 Dev
Kat · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
Coding

What is IQ2_XXS?

Importance-matrix 2-bit quant. Extreme compression with a large quality cost. On average it stores about 2.1 bits per weight, so a IQ2_XXS file is roughly 13% of the size of the same model in 16-bit. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

26,647 models have a IQ2_XXS file on ggufmodels.com, and those files range from 0.0 to 769.1 GB. The most downloaded are Qwen3.8-27B, Qwen3.8 27B and DeepSeek V4.1 Flash 1017 GSQ RCO. For a longer explanation of every quant type, read GGUF quantization explained.

Frequently asked questions

What is IQ2_XXS in GGUF?

Importance-matrix 2-bit quant. Extreme compression with a large quality cost. It averages about 2.1 bits per weight.

Should I use IQ2_XXS?

Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

How big is a IQ2_XXS file?

IQ2_XXS files on this site range from 0.0 to 769.1 GB, depending on the model. As a rule of thumb it is about 13% of the 16-bit size.

Other quants

Keep browsing