Q2_K GGUF models

2-bit k-quant. Smallest files and a clear drop in quality. Use it only when memory is very tight. 112215 models have a Q2_K file. Sizes run from 1M to 2780B parameters. The longest trained context is 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.8-27B
Qwen · huihui-ai
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
MI
MiniMax H3
Minimax · unsloth
Params20B
Context—
Q4_K_M18.2 GB
GGUF
QW
Qwen3.8 27B Uncensored HauhauCS Aggressive MTP
Qwen · HauhauCS
Params30B
Context—
Smallest0.9 GB
GGUF
OR
Ornith 1.5 9B Uncensored
Ornith · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Vision
QW
Qwen Image 2.1
Qwen · unsloth
Params7.12B
Context—
Q4_K_M4.2 GB
GGUF
QW
Huihui Qwen3.6 35B A3B Abliterated
Qwen · huihui-ai
Params35.5B
Context256K
Smallest13.2 GB
Vision
QW
Qwen3.8 35B A3B Distill
Qwen · empero-ai
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningVision
QW
Qwen3.8 Flash Next Uncensored
Qwen · orcarouter
Params177B
Context256K
Q4_K_M119.2 GB
ReasoningTool useVision
MI
MiniMax H3
Minimax · DeepBeepMeep
Params25.8B
Context—
Q4_K_M14.6 GB
GGUF
IM
Z Image Turbo
Image · unsloth
Params6.15B
Context—
Q4_K_M3.9 GB
GGUF
QW
MiMo V2.6 Distill Qwen 9B
Qwen · bartowski
Params8.95B
Context256K
Q4_K_M5.8 GB
CodingTool useVision
QW
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Qwen · HauhauCS
Params34.7B
Context256K
Q4_K_M21.2 GB
Vision
QW
Qwopus3.8 27B Flash V2
Qwopus · Jackrong
Params28B
Context256K
Q4_K_M16.8 GB
CodingReasoningTool use
GE
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
Gemma · HauhauCS
Params7.5B
Context128K
Q4_K_M5.3 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
WA
Wan2.2 I2V A14B
Wan · QuantStack
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
OC
Occamy 1.0
Occamy · Accio-Lab
Params34.7B
Context256K
Q4_K_M21.2 GB
Tool useVision
QW
Qwen Image Edit 2511
Qwen · unsloth
Params20.4B
Context—
Q4_K_M12.8 GB
GGUF
QW
Qwen Image 2.1 Turbo
Qwen · unsloth
Params7.12B
Context—
Q4_K_M4.2 GB
GGUF
QW
Qwen3 VL 8B Instruct Abliterated
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Vision
QW
qwen2.5-7b-instruct
Qwen · Qwen
Params7.6B
Context128K
Q4_K_M4.7 GB
GGUF
SI
Simplicio 27B
Simplicio · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingVision
QW
Qwen Image 2.1 Turbo Uncensored
Qwen · AtomicChat
Params8.19B
Context256K
Smallest3.3 GB
CodingTool useVision
GP
Gpt-Oss-20B
gpt-oss · unsloth
Params20.9B
Context128K
Q4_K_M11.6 GB
GGUF
QW
Swift Qwen3.8 27b
Qwen · ukisai
Params27.3B
Context256K
Q4_K_M18.0 GB
ReasoningVision
YU
YuE2 LM
Yue · scragnog
Params3.8B
Context24K
Q4_K_M2.4 GB
GGUF
NO
nomic-embed-text-v1.5
Nomic · nomic-ai
Params137M
Context2K
Q4_K_M0.1 GB
Embedding
QW
Qwen3-4B
Qwen · unsloth
Params4B
Context40K
Q4_K_M2.5 GB
GGUF
DA
POCKET 35B
Darwin · FINAL-Bench
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF

What is Q2_K?

2-bit k-quant. Smallest files and a clear drop in quality. Use it only when memory is very tight. On average it stores about 3 bits per weight, so a Q2_K file is roughly 19% 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.

112,215 models have a Q2_K file on ggufmodels.com, and those files range from 0.0 to 1009.5 GB. The most downloaded are Qwen3.8-27B, MiniMax H3 and Qwen3.8 27B Uncensored HauhauCS Aggressive MTP. For a longer explanation of every quant type, read GGUF quantization explained.

Frequently asked questions

What is Q2_K in GGUF?

2-bit k-quant. Smallest files and a clear drop in quality. Use it only when memory is very tight. It averages about 3 bits per weight.

Should I use Q2_K?

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 Q2_K file?

Q2_K files on this site range from 0.0 to 1009.5 GB, depending on the model. As a rule of thumb it is about 19% of the 16-bit size.

Other quants

Keep browsing