Q4_K_XL GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 1216 models have a Q4_K_XL file. Sizes run from 1M to 2780B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
GE
gemma 4 26B A4B it qat
Gemma · Hagwell
Params25.2B
Context128K
Smallest0.3 GB
ReasoningTool useVision
ME
Sakura MetaEncoder 30B Experiment
Meta · webmp3
Params27.9B
Context128K
Smallest19.7 GB
CodingEmbeddingReasoning
GE
gemma 4 E4B it heretic
Gemma · meangrinch
Params7.52B
Context128K
Smallest4.5 GB
ReasoningTool use
GE
crislang models
Gemma · yerzer
Params4.63B
Context128K
Smallest2.2 GB
ReasoningTool use
GE
Gemma-4-E2B-It
Gemma · 0x3
Params4.65B
Context128K
Q4_K_M3.1 GB
ReasoningTool useVision
GE
gemma 4 12B it qat GGUF etheroi
Gemma · developerjeremylive
Params11.9B
Context256K
Smallest0.3 GB
ReasoningTool useVision
QW
Qwen3.8-27B
Qwen · 2531oupp
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
QW
Qwen3.8 27B Reflect
Qwen · annnnnnnd
Params27.3B
Context256K
Smallest17.6 GB
ReasoningTool use
QW
vai 8b
Qwen · votal-ai
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
GE
gemma 4 E4B it heretic QAT
Gemma · HTNZ555
Params7.46B
Context128K
Smallest4.3 GB
CodingReasoningTool use
QW
Qwen3.5-4B
Qwen · harsha-math
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
DE
DeepSeek V4 Flash 0731
DeepSeek · speakguru
Params284B
Context1024K
Smallest10.9 GB
GGUF
EV
meituan EvoCUA 32B 20260105
Evocua · spicyneuron
Params32.8B
Context256K
Smallest12.8 GB
ReasoningTool useVision
GP
Gpt-Oss-20B
gpt-oss · Locosdeamor
Params20.9B
Context128K
Q4_K_M11.6 GB
Tool use
GE
Gemma 4 31B StyleTune
Gemma · groxaxo
Params32.1B
Context256K
Smallest19.6 GB
ReasoningTool useVision
GE
Gemma-4-E2B-It
Gemma · heyAadi
Params4.65B
Context128K
Q4_K_M3.1 GB
ReasoningTool useVision
QW
viscer 4b
Qwen · TheWickedGustav
Params4.33B
Context256K
Q4_K_M2.8 GB
ReasoningTool use
GE
Gemma-4-E2B-It
Gemma · redmik60
Params4.65B
Context128K
Q4_K_M3.1 GB
ReasoningTool useVision
LL
Llama 4 Maverick 17B 128E Instruct Projected Abliterated
Llama · nguyenthilaitrieulong
Params401B
Context1024K
Smallest232.2 GB
Tool useVision
JA
Jan-v3-4b-base-instruct
Jan · kushagra909
Params4.41B
Context256K
Q4_K_M2.7 GB
CodingTool use
QW
Qwen3-30B-A3B-Thinking-2507
Qwen · lovedheart
Params30.5B
Context256K
Smallest6.3 GB
ReasoningTool use
JA
Jan v1 2509
Jan · rodrigomt
Params4.02B
Context256K
Smallest2.5 GB
ReasoningTool use
GL
GLM 5.3 Flash
GLM · Nbighir
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
GE
Gemma-4-E4B-It
Gemma · manojbillionaire123
Params7.52B
Context128K
Q4_K_M5.0 GB
ReasoningTool useVision
GP
Neve Sense 2 20B
gpt-oss · NeveAI
Params20.9B
Context128K
Smallest11.9 GB
Tool use
QW
Qwen3.5-27B
Qwen · XpressAI
Params28.4B
Context256K
Smallest18.6 GB
ReasoningTool use
QW
Qwen3.8 Flash Next
Qwen · brianbellx
Params177B
Context256K
Smallest111.3 GB
ReasoningTool useVision
GE
Gemma-4-E2B-It
Gemma · gijl
Params4.65B
Context128K
Q4_K_M3.1 GB
ReasoningTool useVision
DE
DeepSeek V4 Flash 0731
DeepSeek · Stk88
Params284B
Context1024K
Smallest10.9 GB
GGUF
DE
DeepSeek V4 Flash 0731
DeepSeek · lyssquant
Params284B
Context1024K
Smallest10.9 GB
GGUF

Other quants

Keep browsing