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
IN
Internvl3-78B
Internvl · unsloth
Params72.7B
Context32K
Q4_K_M47.4 GB
CodingTool useVision
MU
TQ3.5 27B Musica v1
Musica · bartowski
Params26.9B
Context256K
Q4_K_M17.5 GB
ReasoningRoleplayTool use
GW
GWQ 9B Preview2
Gwq · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
LL
Sparse Llama 3.1 8B 2of4
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Cogito v2 Preview Llama 109B MoE
Llama · bartowski
Params108B
Context256K
Q4_K_M67.7 GB
ReasoningTool use
MI
Mistral Small Instruct 2409 Abliterated
Mistral · bartowski
Params22.2B
Context32K
Q4_K_M13.3 GB
Tool use
MI
MiniMax M2 THRIFT
Minimax · bartowski
Params173B
Context192K
Q4_K_M104.6 GB
CodingReasoningTool use
MI
Magistral-Small-2507
Mistral · unsloth
Params23.6B
Context40K
Q4_K_M14.3 GB
ReasoningTool use
QW
Qwen2.5 3B Instruct
Qwen · zw89
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
QW
nbeerbower Dumpling Qwen2.5 14B
Qwen · bartowski
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
RA
raspberry 3B
Raspberry · bartowski
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
GE
Gemma-3-270M-It
Gemma · Sci-fi-vy
Params268M
Context32K
Q4_K_M0.3 GB
GGUF
CR
Crimson Dawn V0.1
Crimson · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
OL
Olmo-2-0425-1B-Instruct
OLMo · unsloth
Params1.48B
Context4K
Q4_K_M0.9 GB
GGUF
QW
Qwen2 Math 1.5B Instruct
Qwen · bartowski
Params1.54B
Context4K
Q4_K_M1.0 GB
GGUF
QW
Qwen3 30B A3B Mixture 2507
Qwen · bartowski
Params30.5B
Context256K
Q4_K_M18.6 GB
ReasoningTool use
NE
Nera Noctis 12B
Nera · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
EL
EleMo V3 Base
Elemo · Earlychildhoodeducation
Params27.3B
Context256K
Q4_K_M16.5 GB
Vision
LF
LFM2 350M Extract
Lfm · bartowski
Params354M
Context125K
Q4_K_M0.2 GB
Tool use
IN
Internvl3-8B-Instruct
Internvl · unsloth
Params7.61B
Context32K
Q4_K_M4.7 GB
CodingTool useVision
GE
Tiger Gemma 9B v3
Gemma · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
ST
MN 12B Starcannon v3
Starcannon · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
VE
Velvet Eclipse 4x12B v0.2
Velvet · bartowski
Params38.7B
Context1000K
Q4_K_M23.5 GB
Tool use
SN
Snowpiercer 15B v2
Snowpiercer · bartowski
Params15B
Context64K
Q4_K_M9.1 GB
GGUF
MI
MiMo V2.5 Pro
Mimo · bartowski
Params1020B
Context1024K
Q4_K_M622.9 GB
CodingReasoningTool use
CO
Yi Coder 1.5B
Coder · bartowski
Params1.48B
Context128K
Q4_K_M1.0 GB
Coding
GE
RiverCub Gemma 3 27B
Gemma · bartowski
Params27B
Context128K
Q4_K_M16.5 GB
Vision
QW
Qwen3-0.6B
Qwen · openwalrus
Params596M
Context40K
Q4_K_M0.4 GB
ReasoningTool use
LF
LFM2 350M Math
Lfm · bartowski
Params354M
Context125K
Q4_K_M0.2 GB
Tool use
QW
Luau Qwen3 4B FIM v0.1
Qwen · TorpedoSoftware
Params4.02B
Context256K
Smallest2.1 GB
Coding

Other quants

Keep browsing