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
GE
gemma 4 E4B it qat
Gemma · Zagol
Params7.46B
Context128K
Smallest0.1 GB
ReasoningTool useVision
GE
Gemma-4-26B-A4B-It
Gemma · Kivichek
Params25.2B
Context256K
Q4_K_M16.9 GB
ReasoningTool useVision
QW
Qwen3.5-9B
Qwen · madeofhuman
Params8.95B
Context256K
Q4_K_M5.7 GB
ReasoningTool useVision
GE
Gemma-4-E4B-It
Gemma · armandosds
Params7.52B
Context128K
Q4_K_M5.0 GB
ReasoningTool useVision
GE
gemma 4 e2b mobile
Gemma · jeuzu
Params4.63B
Context128K
Smallest0.2 GB
ReasoningTool useVision
DE
Deepseek-R1-Distill-Qwen-1.5B
DeepSeek · Fastiraz
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
QW
Qwen3.8 Flash Next
Qwen · aquaduck
Params77.8B
Context256K
Smallest39.6 GB
ReasoningTool use
EX
EXAONE 4.5 33B DASHQ Q2
Exaone · jkim96
Params32.5B
Context256K
Smallest9.1 GB
GGUF
MU
Muse Glimmer 30B
Muse · Hagwell
Params27.9B
Context128K
Smallest1.6 GB
ReasoningTool useVision
QW
Qwen3.6-27B
Qwen · thy025
Params27.3B
Context256K
Q4_K_M17.1 GB
ReasoningTool useVision
ME
Medgemma-4B-It
Medgemma · Tavorish
Params3.88B
Context128K
Q4_K_M2.5 GB
ReasoningVision
QW
Qwen3.6-27B
Qwen · twizted6665
Params26.9B
Context256K
Q4_K_M16.8 GB
ReasoningTool useVision
LF
Lfm2.5-1.2B-Thinking
Lfm · EmogheneAkpomedaye
Params1.17B
Context125K
Q4_K_M0.7 GB
ReasoningTool use
QW
Qwen3.6-35B-A3B
Qwen · DollasAndSpence
Params34.7B
Context256K
Q4_K_M22.1 GB
ReasoningTool useVision
QW
Qwen3.5-35B-A3B
Qwen · hossamdaoud
Params34.7B
Context256K
Q4_K_M19.9 GB
ReasoningTool useVision
MI
Magistral Small 2509 DASHQ Q2
Mistral · jkim96
Params23.6B
Context128K
Smallest6.8 GB
ReasoningTool use
QW
Qwen3 Next REAP 20B A3B Thinking
Qwen · lovedheart
Params21.7B
Context256K
Smallest0.1 GB
GGUF
QW
Qwen3.8 27B variants dump UD Q2 K XL
Qwen · jjbbeans
Params27.3B
Context256K
Smallest10.7 GB
ReasoningTool use
QW
Qwen3.8 Flash Next
Qwen · KoenKeunen
Params177B
Context256K
Smallest78.9 GB
ReasoningTool use
QW
Qwen3.8-27B
Qwen · lumos12
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
QW
Qwen3.8-27B
Qwen · hanchen1145
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
GE
Gemma-4-E2B-It
Gemma · FamilyDad
Params4.65B
Context128K
Q4_K_M3.1 GB
ReasoningTool useVision
QW
Qwen3.5-0.8B
Qwen · liamhvn
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
QW
Qwen3.8 Flash Next
Qwen · Jamesl0l
Params177B
Context256K
Q4_K_M1.9 GB
ReasoningTool useVision
NO
North-Mini-Code-1.0
North · maxkru92
Params30.5B
Context488K
Q4_K_M19.2 GB
CodingReasoningTool use
QW
Qwen3.6-27B
Qwen · snowwerfer
Params26.9B
Context256K
Q4_K_M16.8 GB
ReasoningTool useVision
GL
GLM 4.7 Flash Coder
GLM · LakoMoor
Params29.9B
Context198K
Smallest9.2 GB
CodingReasoningTool use
GL
GLM 5.2
GLM · eugenep1212
Params754B
Context1024K
Q4_K_M465.8 GB
ReasoningTool use
MI
Minimax-M2.7
Minimax · DSecOperator
Params229B
Context192K
Q4_K_M140.2 GB
ReasoningTool use
QW
Qwen3.5-0.8B
Qwen · Kichu123
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision

Other quants

Keep browsing