Q3_K_XL GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 2589 models have a Q3_K_XL file. Sizes run from 30M to 1050B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
GL
GLM 5.3 Flash
GLM · Ashwinxs
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
IN
Internvl3-14B
Internvl · unsloth
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool useVision
LL
Llama 3.1 70B Instruct Lorablated Creative Writer
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
JA
AI21 Jamba2 3B
Jamba · bartowski
Params3.2B
Context256K
Q4_K_M1.9 GB
Tool use
AS
Assistant_Pepe_8B
Assistant · bartowski
Params8.04B
Context1048K
Q4_K_M4.9 GB
GGUF
JE
Jedi 3B 1080p
Jedi · bartowski
Params3.09B
Context125K
Q4_K_M1.9 GB
Tool useVision
DE
DeepSeek V4 Flash 0731
DeepSeek · Krhuz
Params284B
Context1024K
Smallest10.9 GB
GGUF
GL
GLM 5.3 Flash
GLM · AshwinX
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
CA
Nitral AI Captain Eris Violet GRPO v0.420
Captain · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
LI
Linkbricks Horizon AI Japanese Pro V3 70B
Linkbricks · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
QW
Qwen3-1.7B
Qwen · openwalrus
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
TI
Tigerlily R3
Tigerlily · EnlistedGhost
Params11.8B
Context128K
Q4_K_M6.9 GB
Vision
QW
Qwen2 Math 7B Instruct
Qwen · bartowski
Params7.62B
Context4K
Q4_K_M4.7 GB
GGUF
QW
QwQ 32B ArliAI RpR v1
Qwen · bartowski
Params32.8B
Context40K
Q4_K_M19.9 GB
ReasoningTool use
OL
olmOCR 7B 0225 Preview
OLMo · bartowski
Params7.62B
Context32K
Q4_K_M4.7 GB
Vision
QW
Qwen3.8-27B
Qwen · SwinliQ-AIn-2
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
EX
EXAONE 3.5 2.4B Instruct
Exaone · bartowski
Params2.67B
Context32K
Q4_K_M1.6 GB
GGUF
EL
Ellaria 9B
Ellaria · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
Roleplay
QW
Cogito v1 Preview Qwen 14B
Qwen · bartowski
Params14.8B
Context128K
Q4_K_M9.0 GB
GGUF
LL
Human Like LLama3 8B Instruct
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
HE
HelpingAI2 9B
Helpingai · bartowski
Params8.9B
Context128K
Q4_K_M5.4 GB
Tool use
DA
Dazzling Star Aurora 32b v0.0 Experimental 1130
Dazzling · bartowski
Params32.8B
Context128K
Q4_K_M19.9 GB
Tool use
QW
Qwen3-4B
Qwen · openwalrus
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
QW
Dirk Qwen3.8 27B
Qwen · blackfan23
Params27.3B
Context256K
Smallest8.8 GB
Vision
SM
SmallThinker 4BA0.6B Instruct
Smallthinker · bartowski
Params4.27B
Context32K
Q4_K_M2.6 GB
Tool use
GE
Gemma-4-31B-It
Gemma · Darkknight535
Params30.7B
Context256K
Q4_K_M18.3 GB
ReasoningTool useVision
GE
Gemma-3-12B-It
Gemma · tripolskypetr
Params11.8B
Context128K
Q4_K_M7.3 GB
Vision
LL
Cogito v1 Preview Llama 70B
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
ReasoningTool use
MI
Trinity 2 Codestral 22B
Mistral · bartowski
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
VI
Virtuoso Small
Virtuoso · bartowski
Params14.8B
Context128K
Q4_K_M9.0 GB
Tool use

Other quants

Keep browsing