Q2_K_XL GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 962 models have a Q2_K_XL file. Sizes run from 92M to 2780B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen 36 27
Qwen · havenoammo
Params425M
Context256K
Smallest0.5 GB
GGUF
GE
Gemma-3-1B-It
Gemma · Diasol
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
QW
Qwen3.8-27B
Qwen · rAVEUK
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
QW
Qwen3.8-27B
Qwen · cxc-ryan
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
GE
Gemma-4-31B-It
Gemma · ipsarkar
Params30.7B
Context256K
Q4_K_M18.3 GB
ReasoningTool useVision
QW
Qwen3.8-27B
Qwen · manubc33
Params27.3B
Context256K
Q4_K_M17.1 GB
ReasoningTool useVision
SA
Salience 27B R6 i1
Salience · vectionlabs
Params27.3B
Context1024K
Q4_K_M16.9 GB
CodingReasoningTool use
QW
Qwen3.6-35B-A3B
Qwen · Hagwell
Params35.5B
Context256K
Q4_K_M22.7 GB
ReasoningTool useVision
QW
Qwen3.6-35B-A3B
Qwen · jerpyjerp
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningTool useVision
QW
Qwen3.6-35B-A3B
Qwen · thy025
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningTool useVision
OL
Olmo 3 7B Instruct DASHQ Q2
OLMo · jkim96
Params7.3B
Context64K
Smallest2.3 GB
Tool use
GE
Gemma-4-12B-It
Gemma · senapati484
Params11.9B
Context256K
Q4_K_M7.1 GB
ReasoningTool useVision
QW
Qwen3-4B-Thinking-2507
Qwen · Jeney
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
GE
Gemma-3N-E2B-It
Gemma · Andre2015
Params4.46B
Context32K
Q4_K_M3.0 GB
Vision
QW
Qwen3.8-27B
Qwen · Arslan2703
Params27.3B
Context256K
Smallest8.4 GB
ReasoningTool useVision
GE
gemma-4-E4B-it-heretic-japanese-only
Gemma · JMingo
Params4.56B
Context128K
Q4_K_M3.0 GB
ReasoningTool use
QW
Qwen3.8-27B
Qwen · DonnyFlo85
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
GR
Granite-4.1-30B
Granite · jamiefutch
Params28.9B
Context128K
Q4_K_M17.5 GB
Tool use
GE
Gemma-3-1B-It
Gemma · shehrozrafaqat
Params1B
Context32K
Q4_K_M0.8 GB
GGUF
QW
Qwen3.8 27B Unleashed
Qwen · AleaiactaEst1
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
QW
Qwen3.5-0.8B
Qwen · Xlnk
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
QW
Qwen3.8-27B
Qwen · fyqfy
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
QW
Qwen3.5-0.8B
Qwen · ente-ai
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
CO
Cogito-671B-V2.1
Cogito · unsloth
Params671B
Context160K
Q4_K_M405.4 GB
ReasoningTool use
QW
Qwen3.5-35B-A3B
Qwen · Paul-Wang
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
QW
Qwen3.5-2B
Qwen · Xlnk
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
GE
Gemma-4-12B-It
Gemma · sebidev
Params11.9B
Context256K
Q4_K_M7.1 GB
Vision
QW
Qwen3.6-35B-A3B
Qwen · Deepdive404
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningTool useVision
QW
Qwen3-4B
Qwen · XythicK
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
MI
MiniMax H3
Minimax · JRay0421
Params20.1B
Context—
Q4_K_M18.2 GB
GGUF

Other quants

Keep browsing